© 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. 28192
    Prev
    Next
    INDEX
    Explanations

    incorrect features or simply extras

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

    historical grievances, skeletal structure

    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
     Yacht
    0.48
     ngram
    0.48
     Islanders
    0.47
     Aquaculture
    0.47
    🅰
    0.46
    awai
    0.46
     Invention
    0.45
    icch
    0.45
    لت
    0.45
    ান
    0.44
    POSITIVE LOGITS
    僞
    0.46
    梱包
    0.44
    वक
    0.43
     المك
    0.42
    bec
    0.42
    繁忙時間
    0.42
     forbindelse
    0.41
     {\
    0.41
     gord
    0.41
    kend
    0.41
    Activations Density 0.000%

    No Known Activations