© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26717
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles

    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
     for
    -1.13
     ""){
    -1.08
    と思いました
    -1.07
    それ
    -1.04
     of
    -1.04
     wohin
    -1.01
    ↵↵
    -0.96
    h
    -0.96
    前は
    -0.96
    但却
    -0.92
    POSITIVE LOGITS
    えっ
    1.38
    に追加
    1.19
    を探す
    1.17
    明日は
    1.17
     aguj
    1.17
     obligado
    1.16
    mortar
    1.16
    に使用
    1.14
    からお
    1.14
    $};
    1.12
    Activations Density 0.134%

    No Known Activations