© 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. 66648
    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
    üks
    -1.00
    躇
    -0.97
    веду
    -0.93
     Neil
    -0.91
    скі
    -0.90
    ню
    -0.90
     userSchema
    -0.90
     recuerdo
    -0.89
    lück
    -0.89
    XYGEN
    -0.89
    POSITIVE LOGITS
     реаги
    0.91
     admitir
    0.91
     attacco
    0.90
     観光
    0.88
    bauten
    0.87
     suministros
    0.85
     größe
    0.85
    yot
    0.84
    ☾
    0.82
    づけ
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.