© 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. 12351
    Prev
    Next
    INDEX
    Explanations

    print this

    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
    "
    -3.97
    s
    -3.20
     are
    -3.02
    \
    -2.86
    ↵↵
    -2.70
     I
    -2.59
    ’
    -2.55
     .
    -2.45
        
    -2.41
    ⸥
    -2.39
    POSITIVE LOGITS
    इटम
    3.78
     zelve
    3.27
    囌
    3.08
    婓
    2.81
     verdieping
    2.75
    鴣
    2.75
     geda
    2.73
     magasiner
    2.69
    釭
    2.67
     umbro
    2.64
    Activations Density 0.032%

    No Known Activations