© 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. 101687
    Prev
    Next
    INDEX
    Explanations

    inner core

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

    want to see

    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
    <0xA5>
    0.53
    으로써
    0.49
     こう
    0.48
    ื่น
    0.45
    曉
    0.45
    原来的
    0.45
    LOLLIPOP
    0.45
     วิธี
    0.44
    ციის
    0.44
    লেই
    0.43
    POSITIVE LOGITS
    n
    0.61
    t
    0.57
    as
    0.55
    w
    0.54
    f
    0.53
    u
    0.53
    b
    0.53
    al
    0.49
    er
    0.49
    i
    0.48
    Activations Density 0.001%

    No Known Activations