Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8824
    Prev
    Next
    INDEX
    Explanations

    pi in math formulas

    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
    ‘
    -0.95
     —
    -0.95
    0
    -0.92
    尤其
    -0.91
    ↵↵
    -0.91
    ific
    -0.91
     =
    -0.90
     \
    -0.88
     +
    -0.87
     않았
    -0.85
    POSITIVE LOGITS
     aktivi
    1.09
     parfüm
    1.09
     parfü
    1.09
     vinaigre
    1.05
     organik
    1.05
    ucap
    1.02
     köp
    1.01
     विश्वसनीय
    1.00
     centuries
    0.99
     radians
    0.99
    Activations Density 0.005%

    No Known Activations