© 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. 164652
    Prev
    Next
    INDEX
    Explanations

    springtime, lights, weather

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

    code blocks and quotes

    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
     другом
    0.57
     टाइप
    0.49
    ס
    0.44
    려고
    0.43
    식이
    0.43
     преподава
    0.43
    etas
    0.42
    elin
    0.42
     shir
    0.42
     coax
    0.41
    POSITIVE LOGITS
    பட்ச
    0.51
    𒉡
    0.48
    ホワイト
    0.48
     Begins
    0.48
    上げ
    0.46
     colours
    0.45
    یف
    0.45
     Allerdings
    0.44
    を通して
    0.44
    İlk
    0.44
    Activations Density 0.001%

    No Known Activations