© 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. 10-GEMMASCOPE-RES-131K
    7. 727
    Prev
    Next
    INDEX
    Explanations

    as well

    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_10/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
    ୈ
    -1.98
    ↑↑↑</
    -1.95
     Públicas
    -1.92
    )}
    -1.90
    guigu
    -1.88
    $),
    -1.88
     successively
    -1.84
     hábit
    -1.83
    ’，
    -1.80
    ቍ
    -1.79
    POSITIVE LOGITS
    s
    2.27
     utiliser
    2.22
     
    1.94
    も
    1.92
    ï
    1.86
    [
    1.84
    a
    1.79
    <strong>
    1.77
     一
    1.72
    '
    1.70
    Activations Density 0.001%

    No Known Activations