© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99679
    Prev
    Next
    INDEX
    Explanations

    current replaced unreadable Hom

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

    The neuron activates on numeric tokens (strings containing 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_34/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
    tidase
    -0.88
    Grimm
    -0.86
    Uwagi
    -0.81
    SALUD
    -0.81
    textnormal
    -0.80
    ריך
    -0.78
    感が
    -0.77
    führer
    -0.77
     .$
    -0.76
     pará
    -0.75
    POSITIVE LOGITS
    urator
    0.90
    犷
    0.79
     tuyển
    0.78
     letters
    0.76
    Citiți
    0.76
    MathML
    0.74
     Stardust
    0.74
    Letters
    0.73
    love
    0.72
    了呢
    0.72
    Activations Density 0.000%

    No Known Activations