© 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. 10-GEMMASCOPE-RES-131K
    7. 59469
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    The neuron fires on code tokens involved in assignment expressions (i.e. “=” and the surrounding variable‐assignment context).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Huge
    -1.20
    begin
    -1.18
    recently
    -1.16
     ۱۴۰۰
    -1.16
    similar
    -1.15
    huge
    -1.14
    Losing
    -1.12
     kannst
    -1.11
    Similar
    -1.10
    otherwise
    -1.10
    POSITIVE LOGITS
     when
    1.81
     because
    1.79
     after
    1.68
     with
    1.60
     before
    1.56
     it
    1.44
     what
    1.30
     whenever
    1.27
     Because
    1.23
     did
    1.21
    Activations Density 0.030%

    No Known Activations