© 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. 67220
    Prev
    Next
    INDEX
    Explanations

    parts and specifications

    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
     utilisent
    -1.18
     chemins
    -1.13
     appartiennent
    -1.12
    sucurs
    -1.11
     consideramos
    -1.08
    Wales
    -1.07
    ⅜
    -1.06
    ynchronously
    -1.05
    siones
    -1.05
     considérer
    -1.04
    POSITIVE LOGITS
     some
    1.46
     for
    1.35
     with
    1.33
     also
    1.25
    ampi
    1.23
     también
    1.22
     can
    1.19
    也可以
    1.16
     też
    1.16
     while
    1.14
    Activations Density 0.445%

    No Known Activations