© 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. 22-GEMMASCOPE-RES-131K
    7. 39965
    Prev
    Next
    INDEX
    Explanations

    medical cannabis industry

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

    technical or specialized terms in formal documents or professional contexts.

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

    The neuron fires on numeric or quantitative expressions—numbers, measurements, figure/table labels, and similar technical numeric references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     you
    -1.04
    間違い
    -0.99
    határoz
    -0.92
    детская
    -0.92
    ariato
    -0.88
    almente
    -0.88
     dupla
    -0.86
     cheque
    -0.85
    a
    -0.85
     palme
    -0.84
    POSITIVE LOGITS
     medarbe
    1.00
     lópez
    0.93
    leyen
    0.88
     undergrad
    0.87
     bereiken
    0.86
     tilgjenge
    0.86
    sunday
    0.84
     of
    0.83
    ubei
    0.82
    を見せて
    0.82
    Activations Density 0.021%

    No Known Activations