© 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. 128181
    Prev
    Next
    INDEX
    Explanations

    scores between 0 and 3

    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
     increased
    -0.06
     tireless
    -0.06
     relentlessly
    -0.05
     finans
    -0.05
     शन
    -0.05
     œ
    -0.05
     बाब
    -0.05
     increase
    -0.05
     Examples
    -0.05
    Основные
    -0.05
    POSITIVE LOGITS
    modification
    0.08
     देने
    0.07
    ディレクトリ
    0.06
     utilizzato
    0.06
    ,..
    0.06
     öğretmen
    0.06
     Used
    0.06
     aggior
    0.06
     Legislation
    0.06
     meats
    0.06
    Activations Density 0.002%

    No Known Activations