© 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. 40-GEMMASCOPE-2-RES-262K
    7. 26306
    Prev
    Next
    INDEX
    Explanations

    nextElementSibling or sibling elements

    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/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     McCartney
    0.41
    Saund
    0.40
    時刻
    0.40
     Nid
    0.39
     स्टे
    0.39
    ftime
    0.38
     Anakin
    0.37
    事项
    0.37
    DidEnter
    0.37
    茏
    0.37
    POSITIVE LOGITS
    ().
    0.53
    (':
    0.47
    (":
    0.46
    ":
    0.43
    ()
    0.42
     sho
    0.42
    hemi
    0.41
    ();
    0.40
    ()[
    0.38
    until
    0.38
    Activations Density 0.003%

    No Known Activations