© 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. 14249
    Prev
    Next
    INDEX
    Explanations

    prefetch, vernier, reorganizing, intravenously

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

    lists and titles

    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
    ご覧
    0.47
     досить
    0.44
     ‘
    0.39
     துவ
    0.39
    मी
    0.38
     เปิด
    0.38
     دلچ
    0.38
     واله
    0.38
    📍
    0.37
    ราว
    0.37
    POSITIVE LOGITS
    !!!!!!!!!!!!!!!!
    0.53
     యొక్క
    0.50
     wirelessly
    0.42
    !!!!!!!!
    0.42
     deleterious
    0.41
     decreases
    0.41
     incorrectly
    0.41
     analyses
    0.39
     orally
    0.39
     intravenously
    0.39
    Activations Density 0.257%

    No Known Activations