© 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. 34-GEMMASCOPE-RES-131K
    7. 30558
    Prev
    Next
    INDEX
    Explanations

    Glide, Clyde, or request

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

    The neuron fires on programming‐style tokens (class and method names, punctuation like “.” and “(”, XML tag prefixes, license keywords like “use”, etc.), i.e. code-specific identifiers and syntax.

    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
     cabe
    -0.76
     document
    -0.75
    бно
    -0.75
     Singapura
    -0.74
     largos
    -0.73
    лей
    -0.73
    же
    -0.73
    izat
    -0.72
    تے
    -0.72
     secund
    -0.71
    POSITIVE LOGITS
    リクエスト
    0.88
    cún
    0.80
    meris
    0.79
     εικό
    0.77
    pertino
    0.77
     didn
    0.76
     retribution
    0.76
    Sistema
    0.75
     també
    0.74
     світу
    0.73
    Activations Density 0.004%

    No Known Activations