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. 8504
    Prev
    Next
    INDEX
    Explanations

    code and licenses

    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
    so
    -0.68
    safe
    -0.68
     Chaudh
    -0.67
    è
    -0.66
    PSI
    -0.66
     Amin
    -0.66
     lumps
    -0.65
    ware
    -0.65
     Billi
    -0.65
     FIXED
    -0.64
    POSITIVE LOGITS
    కో
    0.72
    ventilated
    0.70
    wyt
    0.68
    🕟
    0.68
     rompecabezas
    0.67
    shampoo
    0.66
     Babylon
    0.66
     comenzar
    0.66
    Babylon
    0.66
    xfb
    0.66
    Activations Density 0.054%

    No Known Activations