© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38859
    Prev
    Next
    INDEX
    Explanations

    C57BL/6 mouse strain

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

    the number '57' in various contexts such as scientific notation, patent numbers, and mouse strain identifiers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates strongly on numeric tokens (sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exitos
    -2.33
    描く
    -2.31
    先生が
    -2.06
    让我
    -2.05
    ar
    -2.05
    eine
    -2.03
    先生の
    -2.03
    0
    -2.02
    ЧИТА
    -1.98
    ꪻ
    -1.95
    POSITIVE LOGITS
    s
    2.61
    瘣
    1.86
    泺
    1.81
    \%,
    1.80
    ),
    1.80
     französische
    1.79
    zló
    1.77
    銪
    1.73
     trasero
    1.73
    我們
    1.72
    Activations Density 0.018%

    No Known Activations