© 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. 10-GEMMASCOPE-RES-131K
    7. 65128
    Prev
    Next
    INDEX
    Explanations

    command-line interface

    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_10/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
    er
    -2.92
    みよう
    -2.64
     definitive
    -2.52
    CARACTERÍSTICAS
    -2.42
    干什么
    -2.42
    塤
    -2.41
     unequivocal
    -2.41
    зации
    -2.38
    侂
    -2.38
    哢
    -2.34
    POSITIVE LOGITS
    '
    2.67
    𞤢
    2.53
    钐
    2.50
    я
    2.41
    >
    2.38
    蟶
    2.38
    ᕱ
    2.33
    
    2.33
    "}}>
    2.30
    ᜀ
    2.30
    Activations Density 0.005%

    No Known Activations