© 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. 25734
    Prev
    Next
    INDEX
    Explanations

    button and follow-up words

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

    button clicks

    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
    ও
    0.85
    স
    0.71
    도
    0.69
     พิ
    0.67
     my
    0.66
    い
    0.66
     ihe
    0.65
    स
    0.65
     ine
    0.64
    DA
    0.64
    POSITIVE LOGITS
    on
    1.01
    按钮
    0.90
    an
    0.87
    button
    0.77
    less
    0.73
    ón
    0.72
     button
    0.70
    ok
    0.70
    that
    0.70
    rola
    0.67
    Activations Density 0.011%

    No Known Activations