© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11413
    Prev
    Next
    INDEX
    Explanations

    hex codes or identifying numbers

    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
     stratég
    -1.49
     siè
    -1.42
     participó
    -1.39
     desarrolló
    -1.37
     estableció
    -1.36
    
    -1.36
     frança
    -1.35
     presentó
    -1.33
     eenen
    -1.31
    plakat
    -1.30
    POSITIVE LOGITS
    3
    1.58
    1
    1.51
     when
    1.50
     When
    1.47
     as
    1.41
    8
    1.40
     (
    1.35
     by
    1.34
    2
    1.34
    4
    1.32
    Activations Density 0.027%

    No Known Activations