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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11686
    Prev
    Next
    INDEX
    Explanations

    UI components

    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_22/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
    ressors
    -1.03
    uyez
    -0.97
    ieš
    -0.96
     arī
    -0.96
    INCLUD
    -0.94
    esterday
    -0.94
     }^{
    -0.94
    ();
    
    -0.93
     cervello
    -0.92
    Leírás
    -0.90
    POSITIVE LOGITS
     we
    1.04
    c
    0.94
     سبتمبر
    0.87
     garment
    0.85
    we
    0.85
    PN
    0.84
    小孩子
    0.84
    -
    0.83
     já
    0.82
    曲は
    0.82
    Activations Density 0.004%

    No Known Activations