© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 63025
    Prev
    Next
    INDEX
    Explanations

    from, dropped, changes

    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
    गात
    0.42
    ամ
    0.38
    ᆫ
    0.38
    錤
    0.37
    ખી
    0.35
    ulp
    0.35
     ഭരണ
    0.34
    ابعه
    0.34
     ছাড়াই
    0.34
    гия
    0.34
    POSITIVE LOGITS
    从
    1.30
    從
    1.20
     from
    1.16
     từ
    1.16
     From
    1.14
     从
    1.14
    from
    1.13
     från
    1.10
     transition
    1.07
     從
    1.07
    Activations Density 0.003%

    No Known Activations