© 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. 72306
    Prev
    Next
    INDEX
    Explanations

    languages and code snippets

    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
    R
    -1.00
    e
    -0.93
    B
    -0.90
    G
    -0.90
     obligator
    -0.90
     agre
    -0.86
     επι
    -0.84
    と
    -0.84
    t
    -0.83
     auxili
    -0.83
    POSITIVE LOGITS
    ısında
    0.97
     mochilas
    0.97
     ekolog
    0.94
     reservado
    0.93
    cesso
    0.93
     Гри
    0.92
     beeindruck
    0.91
     bekämp
    0.91
     silueta
    0.90
    cú
    0.89
    Activations Density 0.003%

    No Known Activations