© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101279
    Prev
    Next
    INDEX
    Explanations

    contractions like i'm, today's, celebrity'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
     añad
    -2.11
     utiliser
    -1.91
     ajouter
    -1.88
    
    -1.86
     dekol
    -1.86
     acclaimed
    -1.80
     ancienne
    -1.76
     gier
    -1.73
    four
    -1.73
     kulinar
    -1.73
    POSITIVE LOGITS
     with
    2.11
    ＊＊＊＊
    1.91
     cannot
    1.87
     LIABLE
    1.80
     presumably
    1.77
     including
    1.77
     noticeable
    1.74
    责编
    1.74
     on
    1.73
     Obviously
    1.73
    Activations Density 0.198%

    No Known Activations