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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8553
    Prev
    Next
    INDEX
    Explanations

    recycled materials

    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
    ürze
    -0.90
     unlocks
    -0.75
     fixes
    -0.72
    Seasonal
    -0.71
    之后
    -0.71
     wieś
    -0.71
     seguida
    -0.69
    Acesso
    -0.69
     presump
    -0.69
    લી
    -0.68
    POSITIVE LOGITS
     content
    1.39
    content
    1.31
     CONTENT
    1.19
    CONTENT
    1.12
    Content
    1.12
     post
    1.06
    post
    1.03
    ♻
    1.02
    ontent
    0.99
     waste
    0.98
    Activations Density 0.012%

    No Known Activations