© 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. 198524
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and determiners

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

    supposed to, occur while, insert a

    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
    Not in Any Lists

    No Comments

    Negative Logits
     s
    0.56
     riff
    0.54
     bor
    0.49
     reprieve
    0.47
     Jeho
    0.47
     čak
    0.46
     Waits
    0.46
     guns
    0.45
     بق
    0.45
     taj
    0.44
    POSITIVE LOGITS
    locatorType
    0.59
    단체
    0.53
     запуска
    0.52
    resultlist
    0.51
    ǯ
    0.51
    мовір
    0.51
     occup
    0.50
    örungen
    0.49
     kulland
    0.49
     diseñar
    0.49
    Activations Density 0.000%

    No Known Activations