© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14547
    Prev
    Next
    INDEX
    Explanations

    appearance over substance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    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
     ग्रैंड
    0.90
    **
    0.87
     Simplifying
    0.84
     Goal
    0.83
    Simplify
    0.79
    Looking
    0.79
    設計
    0.78
     为了
    0.77
    对
    0.77
    мна
    0.77
    POSITIVE LOGITS
     perforated
    1.00
     recollection
    0.98
     procédé
    0.97
     precaution
    0.96
     ultrasonic
    0.95
    ceased
    0.94
    스와
    0.94
     fellow
    0.93
     frontiers
    0.91
    ഗീയ
    0.91
    Activations Density 0.000%

    No Known Activations