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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5629
    Prev
    Next
    INDEX
    Explanations

    refreshToken, party, headphone, software

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

    This neuron detects numeric tokens—especially numbers with decimal points—where quantitative values appear.

    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
     измене
    0.84
    Hej
    0.84
     misuse
    0.83
     обязан
    0.82
     ቀን
    0.82
    ⚉
    0.82
     FOX
    0.77
    當地
    0.77
    furter
    0.77
     Glück
    0.75
    POSITIVE LOGITS
    اری
    0.83
    ari
    0.73
    дів
    0.71
    ت
    0.71
    ｂ
    0.70
    ྡ
    0.70
    ata
    0.69
     exited
    0.68
    েন্ড
    0.67
    вим
    0.66
    Activations Density 0.000%

    No Known Activations