© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213374
    Prev
    Next
    INDEX
    Explanations

    descriptive terms in technical documents

    np_acts-logits-general · gemini-2.5-flash-lite

    lost or adapt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    amaran
    0.49
    ho
    0.48
    rean
    0.48
    navigations
    0.48
    uretics
    0.48
     विभागों
    0.46
     የተለያዩ
    0.45
    娲
    0.45
    肱
    0.45
    reversible
    0.45
    POSITIVE LOGITS
     ‘
    0.48
     PLE
    0.47
     Lauder
    0.46
     TAR
    0.46
     NAC
    0.45
    Alam
    0.45
     GRAY
    0.45
    僕は
    0.45
    崠
    0.45
     Spent
    0.44
    Activations Density 0.001%

    No Known Activations