© 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. 32079
    Prev
    Next
    INDEX
    Explanations

    Zebra, Zopp, Zipto

    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
    ство
    0.42
     مواليد
    0.42
     створи
    0.40
    ㄾ
    0.40
     सीमित
    0.39
    後の
    0.38
     기본
    0.38
     கண்டுபி
    0.38
    削減
    0.38
    યર
    0.38
    POSITIVE LOGITS
    apatillas
    0.59
     Z
    0.55
    ircon
    0.54
    onedDateTime
    0.52
    Z
    0.44
    eba
    0.43
    usammen
    0.43
    wyczaj
    0.42
    orro
    0.42
    etta
    0.41
    Activations Density 0.006%

    No Known Activations