© 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. 11545
    Prev
    Next
    INDEX
    Explanations

    coding syntax punctuation

    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
     pamoja
    -0.97
    醒了
    -0.91
     fresca
    -0.91
    olanda
    -0.91
     Venise
    -0.90
     Aprend
    -0.90
    ״
    -0.90
    ǂ
    -0.90
    OOOOO
    -0.90
     conva
    -0.90
    POSITIVE LOGITS
     on
    1.02
     yesterday
    0.99
     keperluan
    0.96
    ıyordu
    0.95
     here
    0.94
     estremamente
    0.91
    Hilsen
    0.90
     and
    0.89
    が無
    0.88
     at
    0.87
    Activations Density 0.001%

    No Known Activations