© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 66096
    Prev
    Next
    INDEX
    Explanations

    roots of the Medes

    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
    Negative Logits
    統領
    0.44
    бно
    0.39
     विधानसभा
    0.38
     кін
    0.38
    Vod
    0.38
    బో
    0.38
    ণাস্ত্র
    0.38
     неве
    0.38
    ኖር
    0.37
    ൮
    0.37
    POSITIVE LOGITS
     Av
    0.38
     Approaches
    0.34
     approaches
    0.33
     Sí
    0.33
    ந்து
    0.33
     saling
    0.32
    <i>
    0.32
    Owner
    0.32
     Brother
    0.32
    Av
    0.32
    Activations Density 0.116%

    No Known Activations