© 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. 102841
    Prev
    Next
    INDEX
    Explanations

    demolition

    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
    as
    -2.30
    StoryboardSegue
    -2.27
     bonté
    -2.20
     ALWAYS
    -2.13
    o
    -2.09
     HOW
    -2.08
    didSet
    -2.05
     de
    -2.05
    you
    -2.03
     AFTER
    -2.02
    POSITIVE LOGITS
    ↵
    4.03
    
    2.55
     grün
    2.34
    蟶
    2.31
     angeschlossen
    2.31
    🫅
    2.25
    สอง
    2.22
     cuidadosamente
    2.17
     無料
    2.17
     trois
    2.13
    Activations Density 0.002%

    No Known Activations