© 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. 170500
    Prev
    Next
    INDEX
    Explanations

    strong gains

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

    wasps worried, for services, industry in

    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
     인생
    0.45
     utens
    0.44
     ہوئی
    0.41
     هستند
    0.41
     prohibitive
    0.41
     /ˈ
    0.41
     ਹੈ
    0.40
     Lebesgue
    0.40
     衣
    0.40
    ังสือ
    0.40
    POSITIVE LOGITS
    ň
    0.52
    if
    0.52
    4
    0.51
    iy
    0.49
    AND
    0.48
    customize
    0.48
    COUNTRY
    0.48
    country
    0.48
    t
    0.47
    .*
    0.47
    Activations Density 0.001%

    No Known Activations