© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7395
    Prev
    Next
    INDEX
    Explanations

    HTML doctype declarations

    np_acts-logits-general · gemini-2.5-flash-lite

    html doctype declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })_{\
    0.39
     consideramos
    0.39
     Falcon
    0.38
     Schemes
    0.38
    énés
    0.38
     insc
    0.37
    /__
    0.37
     Ravens
    0.37
     Falcons
    0.37
    SCH
    0.36
    POSITIVE LOGITS
     html
    0.95
     doct
    0.95
    DOCTYPE
    0.91
     HTML
    0.86
    doctype
    0.83
     Doct
    0.82
    <html>
    0.81
    DOCT
    0.76
    HTML
    0.74
     XHTML
    0.73
    Activations Density 0.001%

    No Known Activations