© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146359
    Prev
    Next
    INDEX
    Explanations

    words starting with "i" or "ig"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_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
    破碎
    0.76
     प्रक्रियाओं
    0.72
    तिरिक्त
    0.71
     Broken
    0.69
    亀
    0.69
    broken
    0.69
     broken
    0.69
     ভগ
    0.68
    ృష్టి
    0.68
    藜
    0.67
    POSITIVE LOGITS
    ugoslav
    0.78
     Umlauf
    0.72
    디어
    0.72
    postas
    0.71
     cocktail
    0.71
    premium
    0.70
    rta
    0.68
    itative
    0.68
     postpaid
    0.67
    정한
    0.67
    Activations Density 0.002%

    No Known Activations