© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1113
    Prev
    Next
    INDEX
    Explanations

    years or days

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags numeric tokens and numeric sequences (digits, slashes, and decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numerical digits, especially in sequences like phone numbers, dates, times, and numerical expressions (such as "24 hours a day, 7 days a week, 365 days a year").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    statements indicating round-the-clock availability, such as 24/7 or 24 hours a day, 365 days a year service claims.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     testes
    0.44
     ({\
    0.43
     gaussian
    0.42
     Gaussian
    0.41
     valence
    0.41
    IndexArray
    0.40
     dynamical
    0.39
     lightness
    0.39
     rhenium
    0.38
     deuterium
    0.38
    POSITIVE LOGITS
     অন্যান্য
    0.50
     activités
    0.49
    クリニック
    0.45
     Activities
    0.44
     עם
    0.44
     żad
    0.44
     інші
    0.44
    ंसद
    0.44
     മറ്റ്
    0.43
    Clinic
    0.43
    Activations Density 0.002%

    No Known Activations