© 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. 210312
    Prev
    Next
    INDEX
    Explanations

    Play, system, device, market, price, instructor

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

    complexity, opposition, paid services

    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
     небольшой
    0.46
     potete
    0.46
     глубо
    0.43
    পোর্ট
    0.42
     б
    0.42
     afternoon
    0.42
     корпу
    0.42
     Audubon
    0.41
    ↵
    0.41
     библиоте
    0.41
    POSITIVE LOGITS
    sova
    0.48
     detractors
    0.47
     opponents
    0.45
     Kardash
    0.43
    ractors
    0.41
    offel
    0.40
     complexities
    0.40
    soo
    0.40
     sows
    0.40
    🩷
    0.39
    Activations Density 0.000%

    No Known Activations