© 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. 75731
    Prev
    Next
    INDEX
    Explanations

    material respects

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

    proximity effect

    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
     autoWatch
    0.52
     Lakh
    0.47
     Jacobson
    0.45
    σιο
    0.44
     дизайне
    0.43
     হুমকি
    0.42
     સામાન્ય
    0.42
     گزارش
    0.41
     разработки
    0.41
    :
    0.40
    POSITIVE LOGITS
     RESER
    0.45
    etes
    0.45
    varez
    0.45
     reservation
    0.44
    IVERSITY
    0.43
     til
    0.41
    umber
    0.41
     sweeter
    0.40
     avantages
    0.40
    tering
    0.39
    Activations Density 0.003%

    No Known Activations