© 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. 215400
    Prev
    Next
    INDEX
    Explanations

    proofs, descriptions, definitions

    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
     preci
    0.40
     exists
    0.40
    Exists
    0.40
     существует
    0.39
    俔
    0.38
     istnieje
    0.37
     ค
    0.37
    ilfe
    0.37
    ሕ
    0.37
     siebie
    0.36
    POSITIVE LOGITS
    我还
    0.37
     이용해서
    0.36
     اسكت
    0.35
    网红
    0.35
     inhib
    0.34
    従
    0.34
    翁
    0.34
     attitudes
    0.34
    ASGI
    0.34
     वत्स
    0.34
    Activations Density 0.000%

    No Known Activations