© 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. 27724
    Prev
    Next
    INDEX
    Explanations

    swimming classes, quotations, system data

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

    action, goal, movement, reporting

    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
    are
    0.49
    gestellt
    0.49
    or
    0.49
    be
    0.48
    in
    0.47
    lain
    0.46
     E
    0.46
    non
    0.46
    schlag
    0.45
    roff
    0.45
    POSITIVE LOGITS
    瑆
    0.54
    സർ
    0.52
    າມາດ
    0.51
    League
    0.50
    UG
    0.50
     जीएसटी
    0.50
    趄
    0.50
    तक
    0.50
    财政
    0.49
    联赛
    0.49
    Activations Density 0.001%

    No Known Activations