© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11858
    Prev
    Next
    INDEX
    Explanations

    getting width and layout

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

    The neuron fires on code identifiers (especially CamelCase class‐ or method‐names) rather than natural language words.

    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
    uanya
    -0.81
     RESOURCES
    -0.76
    Whom
    -0.75
    fileInfo
    -0.75
    ể
    -0.75
    NOTAS
    -0.74
    Loy
    -0.73
    zyst
    -0.73
     penned
    -0.73
     Recursos
    -0.73
    POSITIVE LOGITS
    MeasureSpec
    0.93
    measured
    0.84
     measured
    0.81
    getEvent
    0.77
     translocation
    0.74
    ០
    0.71
    Measured
    0.69
    Report
    0.69
    Scheme
    0.69
     left
    0.68
    Activations Density 0.028%

    No Known Activations