© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103431
    Prev
    Next
    INDEX
    Explanations

    code assignment

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

    This neuron detects code tokens involved in function or method invocations (i.e. calls to routines).

    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
    dicht
    -0.99
     PUSTAKA
    -0.92
    NotFoundError
    -0.91
     latter
    -0.91
     ὑ
    -0.91
    Twenty
    -0.90
     komment
    -0.85
     τῆς
    -0.84
     alleen
    -0.83
     same
    -0.83
    POSITIVE LOGITS
     traseiro
    0.98
    ͋
    0.96
     Extragalactic
    0.94
    Verwaltung
    0.93
     also
    0.90
     EXHIB
    0.89
     Referential
    0.89
     Mónica
    0.88
     菇
    0.88
    ロゴ
    0.88
    Activations Density 0.012%

    No Known Activations