© 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. 40005
    Prev
    Next
    INDEX
    Explanations

    list separators

    np_acts-logits-general · gemini-2.5-flash-lite

    src directory paths

    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
     ').
    0.53
    最小
    0.50
    great
    0.46
    quat
    0.46
    choco
    0.45
    不会
    0.45
    hidden
    0.43
     ([
    0.43
     overwritten
    0.42
    paren
    0.42
    POSITIVE LOGITS
     enfermo
    0.47
     fórmula
    0.45
    🌧
    0.45
     лю
    0.45
    。”
    0.44
     tinham
    0.44
     resistentes
    0.44
    MIER
    0.43
     تقديم
    0.43
     hiss
    0.43
    Activations Density 0.000%

    No Known Activations