© 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. 113475
    Prev
    Next
    INDEX
    Explanations

    specific acronyms

    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
    AdvEx
    -2.44
    鱨
    -2.42
    咴
    -2.38
    Ꮌ
    -2.36
    簓
    -2.34
     nya
    -2.30
     BOOKS
    -2.28
     upor
    -2.25
    p
    -2.17
    嫱
    -2.17
    POSITIVE LOGITS
    ),
    2.64
     Pulling
    2.55
    攪
    2.53
    瑗
    2.53
    ه
    2.50
     pervasive
    2.44
    [
    2.42
     Difficult
    2.34
     Throwing
    2.31
     vague
    2.28
    Activations Density 0.003%

    No Known Activations