© 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. 58751
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
    ſelves
    -2.61
    rénées
    -2.42
    孓
    -2.25
    EDEFAULT
    -2.23
    grafías
    -2.20
    lägen
    -2.16
    uteurs
    -2.13
     "";
    -2.11
    dyž
    -2.09
     eğer
    -2.03
    POSITIVE LOGITS
     the
    2.53
     a
    2.39
    v
    2.19
     και
    2.05
    錵
    1.96
    th
    1.95
    n
    1.94
    !
    1.90
    st
    1.89
    r
    1.89
    Activations Density 0.019%

    No Known Activations