© 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. 115983
    Prev
    Next
    INDEX
    Explanations

    computational binding and docking studies

    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
    practice
    -0.06
     educational
    -0.06
    歷史
    -0.06
    Its
    -0.06
     Mortality
    -0.06
    兩種
    -0.06
     মর্যাদা
    -0.06
    リーダー
    -0.06
     खंड
    -0.06
     Arrangements
    -0.06
    POSITIVE LOGITS
     expropri
    0.07
     strategic
    0.07
     strategically
    0.07
    オブジェクト
    0.07
     overlay
    0.06
     targeting
    0.06
    感兴趣
    0.06
     user
    0.06
    Strategic
    0.06
     Fahrzeug
    0.06
    Activations Density 0.021%

    No Known Activations