© 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. 77887
    Prev
    Next
    INDEX
    Explanations

    Tapeworm answers or questions

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

    numerical values in technical or legal documents.

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

    The neuron is primarily triggered by numeric tokens (multi-digit numbers, years, percentages, 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
     When
    -0.72
     >
    -0.72
    二百
    -0.72
     passado
    -0.72
    wissenschaften
    -0.71
    ό
    -0.70
     masjid
    -0.70
    lfloor
    -0.69
    setTimestamp
    -0.69
     gives
    -0.69
    POSITIVE LOGITS
     restes
    0.85
     DANCE
    0.85
    ancies
    0.85
     DOMAIN
    0.84
     domains
    0.84
     atentos
    0.83
     встречи
    0.82
     disques
    0.82
    サート
    0.82
    allowed
    0.82
    Activations Density 0.000%

    No Known Activations