© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 242931
    Prev
    Next
    INDEX
    Explanations

    Hall Memorial Wall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    0.56
    sample
    0.55
    re
    0.53
    schrift
    0.52
     MS
    0.51
    ro
    0.50
    ter
    0.50
    ↵
    0.50
    tart
    0.49
    MS
    0.49
    POSITIVE LOGITS
    ຢ່າງ
    0.57
    Trên
    0.55
     трех
    0.54
     вкус
    0.53
     интерес
    0.50
     применения
    0.50
     ефектив
    0.50
    እን
    0.49
     эффектив
    0.49
     добиться
    0.48
    Activations Density 0.001%

    No Known Activations