© 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. 112862
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    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
     It
    -1.77
    ポイントは
    -1.46
    内容は
    -1.45
    Сколько
    -1.38
     มัน
    -1.38
    entance
    -1.30
     récompense
    -1.24
    ɚ
    -1.23
     itinéraires
    -1.23
    zerland
    -1.22
    POSITIVE LOGITS
    ↵↵
    2.28
    :
    1.54
    L
    1.44
    [
    1.35
     endeavors
    1.27
    ~”
    1.26
    C
    1.23
    useNewUrlParser
    1.23
    "+
    1.22
    ;
    1.22
    Activations Density 0.070%

    No Known Activations