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. 7711
    Prev
    Next
    INDEX
    Explanations

    names and coins

    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
     жид
    -0.76
     ſet
    -0.72
    知道的
    -0.71
    ъ
    -0.70
    alik
    -0.69
    queles
    -0.69
    wsze
    -0.69
     extensively
    -0.67
    uploads
    -0.66
    ert
    -0.66
    POSITIVE LOGITS
     Dread
    1.05
    royal
    1.04
     pinching
    1.02
    Wise
    1.00
    worth
    0.97
     Arcade
    0.96
    Dated
    0.95
    Dread
    0.94
     Penny
    0.94
    wise
    0.92
    Activations Density 0.012%

    No Known Activations