© 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. 178561
    Prev
    Next
    INDEX
    Explanations

    Samuels Chevrolet, Ukraine, screen, garment, Festival

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

    ** from **Data AvailabilityMessage Origination

    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
    uid
    0.49
    innam
    0.48
    خ
    0.46
    aram
    0.46
    ub
    0.46
    utum
    0.46
    inees
    0.45
    u
    0.45
    issa
    0.45
    nd
    0.45
    POSITIVE LOGITS
     दवा
    0.53
     ਯ
    0.51
     ጥላ
    0.51
    רון
    0.50
     півні
    0.50
     sprzedaży
    0.49
    sprecher
    0.48
     prosecution
    0.48
     عادی
    0.48
     городской
    0.48
    Activations Density 0.000%

    No Known Activations