© 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. 120766
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    Not in Any Lists

    No Comments

    Negative Logits
     плюс
    -0.07
     poveć
    -0.07
     build
    -0.06
     supplemented
    -0.06
     المدينة
    -0.06
     '$(
    -0.06
     나의
    -0.06
     سنت
    -0.06
     zusätz
    -0.06
     رشد
    -0.06
    POSITIVE LOGITS
     suspected
    0.06
     телеви
    0.06
     exemplaires
    0.06
     atento
    0.06
     déterminer
    0.06
     Exempl
    0.06
     belirl
    0.06
     tervez
    0.05
     ident
    0.05
     bijz
    0.05
    Activations Density 0.005%

    No Known Activations