© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30472
    Prev
    Next
    INDEX
    Explanations

    Foundation meta

    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
     quelques
    -0.73
     Мак
    -0.72
     maakt
    -0.68
    完成了
    -0.68
    point
    -0.68
     漢
    -0.67
    merksamkeit
    -0.66
     continu
    -0.66
     Le
    -0.66
    Le
    -0.65
    POSITIVE LOGITS
    iej
    0.77
    Реги
    0.77
    
    0.75
    heir
    0.71
    胁
    0.71
     Gå
    0.70
    kian
    0.69
    urich
    0.69
    FTW
    0.68
     asker
    0.68
    Activations Density 0.049%

    No Known Activations