© 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. 109687
    Prev
    Next
    INDEX
    Explanations

    digits and numbers

    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
    二百
    -0.81
     Pierre
    -0.71
     analyze
    -0.70
     klip
    -0.69
     библиоте
    -0.68
    balar
    -0.66
     analyzes
    -0.66
     東京都
    -0.66
    phazard
    -0.66
    estand
    -0.66
    POSITIVE LOGITS
     digits
    3.72
     digit
    3.42
    digits
    2.92
    Digits
    2.84
    digit
    2.78
     Digit
    2.41
    Digit
    2.33
     figures
    2.02
     DIGIT
    1.95
    桁
    1.90
    Activations Density 0.060%

    No Known Activations