© 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. 145339
    Prev
    Next
    INDEX
    Explanations

    lost, turned, prime, copied, began

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

    action phrases and descriptive terms

    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
    ing
    0.49
     humor
    0.49
    全
    0.49
    影片
    0.46
    中
    0.45
    has
    0.45
    ...
    0.44
    吉祥
    0.44
    在
    0.44
     obes
    0.43
    POSITIVE LOGITS
     প্রভ
    0.51
    šanu
    0.50
     ਦਵਾਈ
    0.49
    cję
    0.48
     ತೆಗೆದುಕೊಳ್ಳ
    0.48
     범
    0.47
     ถาม
    0.47
    kiego
    0.46
     주인
    0.46
     преступ
    0.46
    Activations Density 0.000%

    No Known Activations