© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68800
    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
    妖精
    -0.78
     all
    -0.76
    varlak
    -0.76
    дневно
    -0.76
     lastly
    -0.75
    typeorm
    -0.75
    idenz
    -0.73
    ються
    -0.73
     voices
    -0.72
    язы
    -0.72
    POSITIVE LOGITS
    Goed
    0.86
    zyż
    0.86
     partenza
    0.85
    cbb
    0.82
     一覧
    0.81
    Vier
    0.81
    覦
    0.80
    夘
    0.80
    carus
    0.80
    ীয়
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.