© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1970
    Prev
    Next
    INDEX
    Explanations

    final response

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

    The neuron fires on numeric tokens (especially multi‐digit and decimal numbers).

    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_31_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
     chỉ
    0.67
     Chỉ
    0.66
     slechts
    0.64
     tylko
    0.63
    <unused2162>
    0.62
     μόνο
    0.62
     Được
    0.61
    Ს
    0.60
     แอ
    0.60
    ⟥
    0.60
    POSITIVE LOGITS
     |
    0.75
    Downloaded
    0.62
    Copyright
    0.61
    페이지
    0.61
    Page
    0.61
    Ibid
    0.58
     Copyright
    0.58
    page
    0.56
     ibid
    0.56
    ©
    0.54
    Activations Density 0.096%

    No Known Activations