© 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. 93279
    Prev
    Next
    INDEX
    Explanations

    SIC industry classification

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     watches
    -0.79
    raisal
    -0.78
    ømme
    -0.78
    mbg
    -0.76
    Auswahl
    -0.73
     pořád
    -0.73
    chum
    -0.72
    oherty
    -0.72
     Tada
    -0.69
    思議
    -0.68
    POSITIVE LOGITS
     SIC
    2.19
    SIC
    2.09
     industry
    1.93
     industries
    1.63
     NA
    1.63
     Industry
    1.62
    Industry
    1.59
    industry
    1.47
    NA
    1.28
     sic
    1.27
    Activations Density 0.021%

    No Known Activations