© 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. 34-GEMMASCOPE-RES-131K
    7. 109718
    Prev
    Next
    INDEX
    Explanations

    Amazon imported colors

    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_34/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
    ='"
    -0.85
    冥
    -0.84
     http
    -0.71
    vatar
    -0.71
     www
    -0.70
     Even
    -0.69
    notifyListeners
    -0.68
     вкусу
    -0.68
     说
    -0.67
    getch
    -0.67
    POSITIVE LOGITS
     Amazon
    1.27
    Amazon
    1.12
    amazon
    1.12
    ASIN
    1.10
     imported
    1.07
     específica
    1.04
     amazon
    1.03
     Imported
    0.96
     específicas
    0.94
    Imported
    0.91
    Activations Density 0.007%

    No Known Activations