© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3291
    Prev
    Next
    INDEX
    Explanations

    accepting or not accepting cash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ួក
    0.55
    <unused706>
    0.52
    ាតុ
    0.51
    ម្លៃ
    0.51
    ratingBarStyle
    0.51
    arranty
    0.49
    biotics
    0.48
    configuring
    0.48
    quirements
    0.48
    brightness
    0.48
    POSITIVE LOGITS
     more
    0.54
     Medici
    0.50
     Graffiti
    0.50
     both
    0.50
     더
    0.49
     같은
    0.48
     only
    0.47
     one
    0.46
    ད་
    0.46
    뿐
    0.46
    Activations Density 0.001%

    No Known Activations