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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12150
    Prev
    Next
    INDEX
    Explanations

    measurement and tracking

    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_22/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
    之时
    -1.52
     vinaigre
    -1.35
     unsere
    -1.34
    讐
    -1.29
    movieId
    -1.25
    Venezuela
    -1.23
    億円
    -1.20
     السياس
    -1.20
    цтва
    -1.20
     maritime
    -1.19
    POSITIVE LOGITS
     you
    1.84
     your
    1.83
    𝑧
    1.32
     Erkrank
    1.30
     measurements
    1.27
     überprü
    1.23
     daily
    1.23
    titial
    1.22
    感が
    1.21
    namientos
    1.21
    Activations Density 0.048%

    No Known Activations