© 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. 10-GEMMASCOPE-RES-131K
    7. 141
    Prev
    Next
    INDEX
    Explanations

    C3H mice, C3 complement, C3 axis

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

    This neuron detects scientific or technical identifiers/notations involving "C3" or "C4", particularly in chemical, genetic, or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -2.11
     Reglamento
    -1.91
     to
    -1.85
     estadual
    -1.78
    但这
    -1.75
    洐
    -1.73
     Teléfono
    -1.72
    .
    -1.69
     Redacción
    -1.68
    但却
    -1.68
    POSITIVE LOGITS
     ваш
    2.09
    s
    1.83
    //
    1.80
    i
    1.77
     eben
    1.73
    va
    1.70
    鋱
    1.66
            
    1.66
    ズの
    1.63
    derdag
    1.63
    Activations Density 0.016%

    No Known Activations