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. 8914
    Prev
    Next
    INDEX
    Explanations

    star ratings and scores

    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
    ésar
    -0.85
    Tembelea
    -0.76
    มาะ
    -0.73
    합
    -0.73
    образие
    -0.73
    льних
    -0.72
    vesen
    -0.71
    ‣
    -0.71
     ire
    -0.71
    那么
    -0.70
    POSITIVE LOGITS
     zero
    1.30
     rating
    1.27
    ZERO
    1.19
    give
    1.17
    Give
    1.13
     five
    1.12
    Rating
    1.10
     zéro
    1.10
     more
    1.09
    zero
    1.09
    Activations Density 0.004%

    No Known Activations