© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40244
    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
    にしました
    -1.06
    gione
    -1.00
     Somers
    -0.94
    БК
    -0.94
    我没
    -0.94
     ignores
    -0.94
    になったら
    -0.93
     hagy
    -0.91
     tamam
    -0.90
    pergillus
    -0.90
    POSITIVE LOGITS
     and
    1.32
     rất
    1.07
    があり
    0.96
     детская
    0.95
     Конечно
    0.94
    dsquared
    0.91
     algumas
    0.91
    iferous
    0.90
    러나
    0.90
     velmi
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.