© 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. 76229
    Prev
    Next
    INDEX
    Explanations

    defending player

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

    describes builder demonstrates, Unwound

    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
     решений
    0.55
     í
    0.49
     い
    0.47
     gorge
    0.47
    ç
    0.47
    ci
    0.46
     کاری
    0.46
     ترکیب
    0.45
     مع
    0.44
     تت
    0.44
    POSITIVE LOGITS
     Гинд
    0.49
    成功
    0.48
     Insulin
    0.48
     Glendale
    0.46
     McFarland
    0.46
    瞟
    0.45
    थाल
    0.45
     Magdeburg
    0.45
    runde
    0.45
     Guardians
    0.44
    Activations Density 0.000%

    No Known Activations