© 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. 152896
    Prev
    Next
    INDEX
    Explanations

    size, he, tailor, reason, largest

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

    general overview or idea

    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
    s
    0.52
    h
    0.48
    스
    0.47
     fles
    0.47
     minhas
    0.47
     juh
    0.46
    Xaml
    0.45
     casado
    0.45
     cadeira
    0.45
    返
    0.44
    POSITIVE LOGITS
     XVI
    0.45
    ,“
    0.44
     Ethiopia
    0.44
     আদর্শ
    0.44
     વિક
    0.44
     Africans
    0.44
     Abu
    0.43
     সূচনা
    0.42
    ocity
    0.42
    IELD
    0.42
    Activations Density 0.000%

    No Known Activations