© 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. 106398
    Prev
    Next
    INDEX
    Explanations

    forthcoming publication

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

    mean when

    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
     <
    0.56
     Plusieurs
    0.48
     ->
    0.47
     pregnant
    0.46
     relativ
    0.44
     \
    0.44
     en
    0.44
     =
    0.43
     Vo
    0.43
     Note
    0.43
    POSITIVE LOGITS
    ریان
    0.52
    សម្រាប់ការ
    0.52
     қо
    0.50
    अमेरिकी
    0.50
     अमेरिकी
    0.49
    ahooks
    0.49
    რობ
    0.49
    щенко
    0.48
     ফর
    0.47
     банк
    0.47
    Activations Density 0.001%

    No Known Activations