© 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. 41544
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    珖
    -2.84
     or
    -2.73
    warnai
    -2.70
    摇了
    -2.56
     fueran
    -2.50
    زندگی
    -2.50
     bzw
    -2.48
    इटम
    -2.36
    爱的
    -2.20
    ญี่ป
    -2.20
    POSITIVE LOGITS
    s
    3.70
    "—
    2.75
    了
    2.69
    ים
    2.45
    .’
    2.27
    紲
    2.23
    z
    2.23
    e
    2.17
     

    2.17
     become
    2.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.