© 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. 56622
    Prev
    Next
    INDEX
    Explanations

    method, loop, commit, avg, copied

    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
    ramatta
    0.46
    糉
    0.44
     dalamnya
    0.42
     डिलिवरी
    0.41
     bhfuil
    0.41
     freighter
    0.40
     ၊
    0.40
    carbons
    0.39
     เนาะ
    0.39
     τὸ
    0.38
    POSITIVE LOGITS
    n
    0.38
    Sign
    0.36
    (:,
    0.36
    Consider
    0.36
    Deb
    0.35
    lists
    0.34
    Still
    0.32
    Sin
    0.32
    .”
    0.32
    Lists
    0.32
    Activations Density 0.000%

    No Known Activations