© 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. 26328
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     лет
    -1.03
     one
    -0.96
    لط
    -0.92
     numberOf
    -0.91
    寰
    -0.91
     vanske
    -0.89
     زیادی
    -0.87
    blume
    -0.87
     trimestre
    -0.87
    oprot
    -0.87
    POSITIVE LOGITS
    íficos
    1.06
     asemenea
    1.02
    probably
    1.02
     probabilmente
    1.01
     {?}
    1.00
    說道
    1.00
    étaient
    0.97
    羮
    0.96
     poussière
    0.96
     funcionamiento
    0.96
    Activations Density 0.000%

    No Known Activations