© 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. 128408
    Prev
    Next
    INDEX
    Explanations

    javascript function

    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
    RICULUM
    -1.21
     kral
    -1.21
    LAX
    -1.10
    горит
    -1.09
    RICT
    -1.06
    元年
    -1.05
    lierten
    -1.04
     fön
    -1.04
    ума
    -1.04
    arkt
    -1.04
    POSITIVE LOGITS
     irány
    1.27
    [
    1.17
     herunterladen
    1.05
     thẻ
    1.04
    .
    1.02
    ”
    0.98
     felé
    0.97
    ↵↵
    0.96
     gedaan
    0.96
     megsz
    0.94
    Activations Density 0.002%

    No Known Activations