© 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. 34-GEMMASCOPE-RES-131K
    4. 109778
    Prev
    Next
    INDEX
    Explanations

    react and styling

    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_34/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
     シー
    -0.77
    Volumen
    -0.77
    olare
    -0.72
    Reprodução
    -0.71
    indir
    -0.71
    けん
    -0.70
     españoles
    -0.70
     firebaseConfig
    -0.69
     гром
    -0.69
    𝓈
    -0.69
    POSITIVE LOGITS
     Theme
    1.34
     styled
    1.23
     Provider
    1.20
    ThemeProvider
    1.13
    Theme
    1.10
    styled
    1.08
     Styled
    1.08
    Provider
    1.07
    jss
    1.06
     theme
    1.04
    Activations Density 0.054%

    No Known Activations