© 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. 34-GEMMASCOPE-RES-131K
    7. 25671
    Prev
    Next
    INDEX
    Explanations

    programming, styling, fashion

    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
    odenal
    -0.82
    òng
    -0.77
    configFile
    -0.74
    ственными
    -0.72
    جهة
    -0.72
     wrapper
    -0.72
    wrapper
    -0.72
     shock
    -0.69
     pedals
    -0.68
    rąg
    -0.68
    POSITIVE LOGITS
     styles
    1.16
     styling
    1.16
     garment
    1.09
     Styling
    0.99
     wearer
    0.98
    yaç
    0.97
     fashion
    0.96
     scalp
    0.94
     návr
    0.93
     shampoo
    0.93
    Activations Density 0.009%

    No Known Activations