© 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. 90791
    Prev
    Next
    INDEX
    Explanations

    system and name Smith

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

    data translation or system data

    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
    i
    0.70
    Ray
    0.49
    e
    0.48
     bibendum
    0.45
     Classroom
    0.43
    an
    0.43
     boardroom
    0.43
     insight
    0.42
     Relationship
    0.42
     by
    0.42
    POSITIVE LOGITS
     কার্য
    0.51
    ƙ
    0.49
     റ
    0.48
    itemId
    0.47
     তদন্ত
    0.47
     യാത്ര
    0.47
    fieldText
    0.47
     सांगतात
    0.47
     dran
    0.47
    ৪
    0.46
    Activations Density 0.000%

    No Known Activations