© 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. 90785
    Prev
    Next
    INDEX
    Explanations

    yahoo

    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
    侂
    -3.16
     famed
    -3.06
     VERY
    -3.06
     But
    -3.05
     startling
    -3.03
     Fünf
    -3.02
     แต่
    -2.97
    晙
    -2.89
    selbe
    -2.88
    蛱
    -2.88
    POSITIVE LOGITS
    {
    3.17
     itſelf
    2.98
    硨
    2.77
    }
    2.50
    `
    2.50
    鱟
    2.47
    ad
    2.36
    💋
    2.33
     PARTE
    2.30
    k
    2.28
    Activations Density 0.003%

    No Known Activations