© 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. 72831
    Prev
    Next
    INDEX
    Explanations

    JavaScript module loading with require

    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
    CHARS
    -0.90
     puzzles
    -0.86
     covid
    -0.86
     יְ
    -0.86
    蓠
    -0.85
     черно
    -0.84
    мә
    -0.84
    INDICATOR
    -0.84
    kond
    -0.82
     saga
    -0.82
    POSITIVE LOGITS
     with
    1.14
     especially
    1.13
    危險
    1.05
     without
    1.04
     how
    1.03
     terutama
    1.01
     khususnya
    1.00
     particularly
    1.00
     what
    0.96
    ★★★
    0.96
    Activations Density 0.082%

    No Known Activations