© 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. 22-GEMMASCOPE-RES-131K
    7. 129248
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens (integer or decimal literals) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     inalámb
    -1.05
     徒歩
    -1.03
    RDONLY
    -1.02
    に行ってきました
    -0.95
    ってみました
    -0.95
     pioneers
    -0.95
     kormány
    -0.93
    träd
    -0.92
    хран
    -0.92
    を示
    -0.91
    POSITIVE LOGITS
     to
    1.16
    generating
    1.13
     hedef
    1.13
     bahkan
    1.10
     ぐ
    1.08
     nawet
    1.05
     journalistes
    1.04
     marié
    1.04
    篝
    1.01
     Generate
    0.95
    Activations Density 0.072%

    No Known Activations