© 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. 78983
    Prev
    Next
    INDEX
    Explanations

    Category

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

    The neuron activates on isolated multi‐digit numeric tokens (e.g. the big numbers appearing in category or metadata lines).

    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
     »)
    -0.89
     that
    -0.88
    embal
    -0.83
     for
    -0.82
    antası
    -0.80
    noteq
    -0.79
     fortfarande
    -0.78
    ″]
    -0.78
    >`;
    -0.78
     again
    -0.77
    POSITIVE LOGITS
    <table>
    1.81
    <h2>
    1.41
    Catégorie
    0.98
     wikipagina
    0.97
    <h3>
    0.91
     template
    0.90
    :<
    0.88
     normes
    0.87
    Categories
    0.86
    template
    0.85
    Activations Density 0.014%

    No Known Activations