© 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. 442
    Prev
    Next
    INDEX
    Explanations

    project build files

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

    The neuron fires on standalone numeric tokens (digit sequences), such as version numbers or numbered path segments.

    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
    @"
    -0.86
    gutter
    -0.73
    ضب
    -0.73
    Bradford
    -0.71
    Eles
    -0.71
     editados
    -0.70
     legalized
    -0.69
    ankind
    -0.69
    ambition
    -0.69
     پاک
    -0.68
    POSITIVE LOGITS
     app
    1.28
    app
    1.19
    build
    0.98
     build
    0.92
    lich
    0.85
     приложение
    0.82
    APP
    0.82
     buildup
    0.80
     wearer
    0.75
    ModuleName
    0.73
    Activations Density 0.035%

    No Known Activations