© 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. 118188
    Prev
    Next
    INDEX
    Explanations

    contrasting descriptions

    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
     reconoce
    -0.95
     бампер
    -0.94
    weisung
    -0.92
     flowery
    -0.92
    ズの
    -0.92
    boxed
    -0.89
     ersche
    -0.88
    dero
    -0.88
     incluye
    -0.87
    mayer
    -0.86
    POSITIVE LOGITS
     сахара
    1.01
     contraste
    0.93
     assur
    0.92
     contrasting
    0.91
    Voilà
    0.90
     profiter
    0.90
     contrast
    0.90
    endurch
    0.89
     chocolat
    0.87
     Hospice
    0.86
    Activations Density 0.034%

    No Known Activations