© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85564
    Prev
    Next
    INDEX
    Explanations

    using Alcohol

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

    code and technical documentation formatting.

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

    The neuron fires on CamelCase API or library class identifiers (e.g. Java class names) in 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_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
    璝
    -2.72
    昻
    -2.72
     hunde
    -2.52
    ization
    -2.30
     faſt
    -2.22
     chère
    -2.20
     ſou
    -2.19
     industriales
    -2.14
    
    -2.11
     grij
    -2.09
    POSITIVE LOGITS
    in
    2.98
    on
    2.38
    where
    2.33
    AN
    2.11
    an
    2.11
    EL
    2.05
    with
    1.99
    OR
    1.98
    IL
    1.95
    end
    1.93
    Activations Density 0.000%

    No Known Activations