© 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. 74803
    Prev
    Next
    INDEX
    Explanations

    still or not expressed

    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
     שלנו
    -1.24
     فقط
    -1.23
    LEBR
    -1.16
    très
    -1.15
     тільки
    -1.14
    ungkap
    -1.14
    кухня
    -1.12
     afbeeldingen
    -1.11
     tylko
    -1.10
    deauna
    -1.10
    POSITIVE LOGITS
     there
    1.52
     in
    1.49
     any
    1.45
    ;
    1.43
     up
    1.43
     it
    1.38
     on
    1.34
     широкий
    1.32
     ever
    1.24
     anyone
    1.21
    Activations Density 0.181%

    No Known Activations