© 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. 172987
    Prev
    Next
    INDEX
    Explanations

    processed EMS

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

    specific details, issues

    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
     部分
    0.54
    ኘ
    0.49
    canon
    0.48
    つい
    0.48
    ăți
    0.46
    را
    0.46
    つける
    0.46
     dour
    0.45
    AlignCenter
    0.43
     тяжё
    0.43
    POSITIVE LOGITS
    ς
    0.52
    VILLE
    0.51
    रूप
    0.50
    LET
    0.48
    Decl
    0.48
     deje
    0.46
    ITH
    0.45
    decl
    0.44
     regularmente
    0.43
    REACTOR
    0.43
    Activations Density 0.001%

    No Known Activations