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. 8618
    Prev
    Next
    INDEX
    Explanations

    Deployment, shortcut icon, Pressure injections, Leigh Vial

    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
    Unlike
    -1.13
     After
    -1.07
     When
    -1.05
    Three
    -1.03
    Aside
    -0.99
    Most
    -0.98
    Some
    -0.95
    During
    -0.94
    There
    -0.93
    Two
    -0.93
    POSITIVE LOGITS
    
    0.98
    Pixmap
    0.97
    ⌵
    0.96
    の中の
    0.94
    参见
    0.93
    bex
    0.93
    included
    0.90
    ステム
    0.89
     BRO
    0.89
     
    0.88
    Activations Density 0.000%

    No Known Activations