© 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. 59525
    Prev
    Next
    INDEX
    Explanations

    code identifiers

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

    The neuron activates on numeric literal tokens (numbers) in code.

    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
     for
    -1.16
     a
    -1.03
    ,
    -0.93
     désolés
    -0.89
     according
    -0.85
    などが
    -0.85
     also
    -0.84
     on
    -0.84
    などを
    -0.84
    パフォーマンス
    -0.84
    POSITIVE LOGITS
    corrhi
    1.33
     män
    1.24
     januari
    1.23
    taient
    1.23
     februari
    1.18
    sistent
    1.17
    ようになった
    1.16
     datter
    1.16
    際に
    1.15
    様な
    1.15
    Activations Density 0.081%

    No Known Activations