© 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. 128258
    Prev
    Next
    INDEX
    Explanations

    review conducted

    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
    设计的
    -0.06
    ospheres
    -0.06
     뛰어
    -0.06
     tone
    -0.06
     कार्याल
    -0.06
     linking
    -0.06
    ispielsweise
    -0.06
    ♥♥
    -0.06
     অধিবেশ
    -0.06
     :-)
    -0.06
    POSITIVE LOGITS
     continued
    0.07
     facteurs
    0.06
     наблю
    0.06
     occurred
    0.06
     প্রত্যক্ষ
    0.06
     occured
    0.06
     কান্না
    0.06
    enz
    0.06
     observación
    0.06
     existe
    0.06
    Activations Density 0.001%

    No Known Activations