© 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. 58525
    Prev
    Next
    INDEX
    Explanations

    ASAP Bari, vein smooth, von Willebrand factor

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

    copyright and licensing statements in source code files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric literals (digit sequences) in code or markup, e.g. standalone numbers in annotations, copyright years, meta content values, etc.

    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
     Felipe
    -0.80
    [
    -0.79
    ([
    -0.76
    [][
    -0.74
    mai
    -0.73
    digital
    -0.69
     $[\
    -0.68
     satunya
    -0.68
     Kenny
    -0.67
    ០
    -0.65
    POSITIVE LOGITS
    繡
    0.73
    륙
    0.71
    打開
    0.70
    inor
    0.69
     organizador
    0.67
     fundador
    0.67
    ↨
    0.66
     zawiera
    0.66
     দেখ
    0.66
    jutnya
    0.65
    Activations Density 0.092%

    No Known Activations