© 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. 84403
    Prev
    Next
    INDEX
    Explanations

    import statements

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

    The neuron activates on numeric literals (sequences of digits) in the code.

    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
     {
    -0.97
    TRIBUN
    -0.94
     justru
    -0.93
    ;%%
    -0.93
    perrt
    -0.86
    isez
    -0.85
     nettsted
    -0.84
    Från
    -0.82
     suivie
    -0.82
    RÉ
    -0.82
    POSITIVE LOGITS
     and
    1.23
     such
    0.89
     these
    0.88
    های
    0.84
     takiej
    0.84
    crumbs
    0.82
    칙
    0.81
     hombros
    0.81
     ألمانيا
    0.81
     merve
    0.81
    Activations Density 0.078%

    No Known Activations