© 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. 192015
    Prev
    Next
    INDEX
    Explanations

    final ruler

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

    share or duration

    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
     สนาม
    0.47
     ಕಾರ್
    0.47
     образование
    0.46
    idene
    0.46
    巿
    0.46
     этапе
    0.46
     വി
    0.46
     ব্যাঙ্ক
    0.45
    ickness
    0.45
     trate
    0.44
    POSITIVE LOGITS
    También
    0.45
     recognized
    0.45
    】
    0.44
    वे
    0.43
    で使用
    0.43
     conm
    0.43
     grudge
    0.43
     multit
    0.42
     hashed
    0.42
    Cuáles
    0.42
    Activations Density 0.001%

    No Known Activations