© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120974
    Prev
    Next
    INDEX
    Explanations

    200 success with errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    两年
    -0.07
     requiere
    -0.06
    ᱨ
    -0.06
    등록
    -0.06
    を一
    -0.06
     aucun
    -0.06
     등록
    -0.06
     及び
    -0.06
    umboldt
    -0.06
    啻
    -0.05
    POSITIVE LOGITS
     secreto
    0.06
     barrio
    0.05
    জানা
    0.05
    ल्फ
    0.05
     sorted
    0.05
     লিখ
    0.05
    çons
    0.05
     terá
    0.05
     Glastonbury
    0.05
     mastery
    0.05
    Activations Density 0.001%

    No Known Activations