© 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. 108320
    Prev
    Next
    INDEX
    Explanations

    code comments and license texts

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

    The neuron fires on numeric tokens (years, version numbers, counts, and other digit‐containing literals).

    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
     attended
    -0.85
    مل
    -0.79
     critical
    -0.76
     materials
    -0.76
     Newtonsoft
    -0.74
     annat
    -0.74
    ry
    -0.73
    ERICAN
    -0.73
     versus
    -0.73
    Der
    -0.73
    POSITIVE LOGITS
    颚
    0.93
     +"
    0.90
    +"
    0.88
    īts
    0.88
     OGSÅ
    0.85
    mittags
    0.84
    を書く
    0.84
     DONE
    0.83
    ∬
    0.82
    März
    0.81
    Activations Density 0.015%

    No Known Activations