© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38968
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax

    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
    gruß
    -1.40
    Various
    -1.27
    About
    -1.24
    gruss
    -1.20
    ႐
    -1.20
    各种
    -1.19
    возмо
    -1.17
    𖣘
    -1.17
    writeHead
    -1.17
    ...)
    -1.17
    POSITIVE LOGITS
     LIBR
    1.12
     khoan
    1.09
     LUMI
    1.09
    HAIR
    1.07
    嗲
    1.06
     itinéraire
    1.05
     doigts
    1.05
     Stare
    1.04
     zustand
    1.03
     tiling
    1.02
    Activations Density 0.218%

    No Known Activations