© 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. 2255
    Prev
    Next
    INDEX
    Explanations

    nearest to hundred, cent, whole

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

    The neuron selectively activates on tokens that are decimal numbers (numeric tokens containing a “.”), i.e. floating-point numerals.

    oai_token-act-pair · o4-miniTriggered 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
    денциа
    0.63
     অত্যন্ত
    0.62
     ایش
    0.61
    PatientR
    0.61
    ♰
    0.59
    ကြား
    0.59
    ۵
    0.57
    ції
    0.57
     цю
    0.57
    entreprise
    0.57
    POSITIVE LOGITS
     deflection
    0.67
     be
    0.63
     consect
    0.61
     accordance
    0.61
     advantage
    0.60
     halves
    0.59
     representation
    0.59
    0.58
     point
    0.57
     clockwise
    0.57
    Activations Density 0.000%

    No Known Activations