© 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. 11534
    Prev
    Next
    INDEX
    Explanations

    specialized vocabulary

    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
    ulsi
    -1.08
     kemudian
    -0.95
     rer
    -0.94
     animado
    -0.93
    venido
    -0.91
    еремо
    -0.88
     保護
    -0.87
    ój
    -0.87
     these
    -0.87
     These
    -0.86
    POSITIVE LOGITS
     majest
    0.98
     perpé
    0.91
     krop
    0.91
     écla
    0.87
     tím
    0.86
     kapac
    0.85
    tiple
    0.84
    谞
    0.84
     énorm
    0.84
     klat
    0.82
    Activations Density 0.069%

    No Known Activations