© 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. 26977
    Prev
    Next
    INDEX
    Explanations

    Revolutionary Soldier, the entire, a capital

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

    while not always

    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
    닛
    0.60
    چے
    0.52
    हे
    0.46
    당
    0.45
    چ
    0.44
     write
    0.44
    گه
    0.44
    ーク
    0.44
    デ
    0.43
    write
    0.43
    POSITIVE LOGITS
     अभ्यर्थ
    0.53
     Cura
    0.52
     午前
    0.49
     mengangkat
    0.49
     nabíd
    0.49
     бла
    0.48
     стимули
    0.48
     ข้าง
    0.47
     funkce
    0.47
     možno
    0.47
    Activations Density 0.000%

    No Known Activations