© 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. 22-GEMMASCOPE-RES-131K
    7. 34179
    Prev
    Next
    INDEX
    Explanations

    DO NOT modify

    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_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
    ITÀ
    -0.98
    cunt
    -0.95
     každý
    -0.94
    ·
    -0.93
     medarbe
    -0.93
     then
    -0.91
    vox
    -0.91
     huelga
    -0.87
     sensación
    -0.87
     mochila
    -0.87
    POSITIVE LOGITS
    car
    0.80
     cren
    0.80
    ງ
    0.79
    യ
    0.79
    ა
    0.78
     anecdotes
    0.77
    worth
    0.77
     autori
    0.77
    érie
    0.75
     foss
    0.75
    Activations Density 0.000%

    No Known Activations