© 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. 22-GEMMASCOPE-RES-131K
    7. 16291
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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_22/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
     it
    -2.56
     akin
    -2.17
    ๖
    -1.93
    utilité
    -1.83
     garner
    -1.83
     that
    -1.83
     comprising
    -1.80
    他說
    -1.79
    ''
    -1.78
     unquestionably
    -1.78
    POSITIVE LOGITS
    th
    2.63
     individuelle
    2.36
     แต่
    2.33
    ۣ
    2.19
     lokale
    2.13
    矗
    2.11
    "،
    2.09
    是非常
    2.09
    ll
    2.09
    co
    2.09
    Activations Density 0.342%

    No Known Activations