© 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. 94460
    Prev
    Next
    INDEX
    Explanations

    language and specific terms

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

    generally better or organized

    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
    damageCount
    0.48
    )-\
    0.47
     Гра
    0.46
     malad
    0.45
    ophil
    0.45
     Factors
    0.45
     ବ
    0.45
    ()],
    0.44
     እንደሚ
    0.44
    ∠
    0.43
    POSITIVE LOGITS
    乐
    0.50
    Drug
    0.49
     Delphi
    0.49
     ایت
    0.49
     lab
    0.48
    药
    0.47
    Kum
    0.47
    अपने
    0.46
     kum
    0.46
     क्लास
    0.46
    Activations Density 0.000%

    No Known Activations