© 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. 80830
    Prev
    Next
    INDEX
    Explanations

    [video] or [pdf] or [NOOK Book] or [corrected] or [AUDIO] or [Download]

    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
    坚决
    -1.22
     drept
    -1.22
     dlouho
    -1.20
     imple
    -1.20
     ushered
    -1.18
     consommate
    -1.16
    絎
    -1.16
    捎
    -1.11
     reaſon
    -1.11
     communicates
    -1.11
    POSITIVE LOGITS
     like
    1.52
    );*/
    1.43
     We
    1.30
    zbęd
    1.28
    rupal
    1.27
    ך
    1.27
    cised
    1.27
     that
    1.26
     This
    1.24
     diesem
    1.22
    Activations Density 0.008%

    No Known Activations