© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12057
    Prev
    Next
    INDEX
    Explanations

    possessive marker 's'

    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
     of
    -2.03
     then
    -1.41
     would
    -1.34
     also
    -1.27
     This
    -1.27
     for
    -1.22
     often
    -1.21
     ''
    -1.18
     even
    -1.18
     However
    -1.16
    POSITIVE LOGITS
     ")");
    1.59
    pergillus
    1.45
    }`;
    1.43
     defekt
    1.43
    panzer
    1.42
    cension
    1.41
    chemia
    1.39
    %");
    1.38
    %"),
    1.38
    promises
    1.38
    Activations Density 0.074%

    No Known Activations