© 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. 130116
    Prev
    Next
    INDEX
    Explanations

    binge watching

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

    feelings, names, and entities

    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
    ્ટ
    0.49
     ولی
    0.46
    c
    0.46
     кай
    0.45
    dus
    0.44
    ulosic
    0.43
    ctuation
    0.43
    дку
    0.43
    д
    0.43
     vadanti
    0.43
    POSITIVE LOGITS
     week
    0.49
     Woche
    0.49
     Chiến
    0.48
     month
    0.46
    لاعب
    0.46
     finde
    0.45
     চ্যাম্প
    0.45
    結婚
    0.45
     Knight
    0.44
    يمكن
    0.44
    Activations Density 0.005%

    No Known Activations