© 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. 116160
    Prev
    Next
    INDEX
    Explanations

    achievement motivation

    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
    立法
    -0.06
     necessariamente
    -0.06
     opposing
    -0.05
    delivery
    -0.05
     ஒவ்வொரு
    -0.05
     block
    -0.05
     terrified
    -0.05
     untuk
    -0.05
     contradictory
    -0.05
    中国
    -0.05
    POSITIVE LOGITS
    Throughout
    0.07
    ⓪
    0.06
     throughout
    0.06
     такой
    0.06
     मुस्
    0.06
     großen
    0.06
    事物
    0.06
     Throughout
    0.06
    的な
    0.06
     довольно
    0.06
    Activations Density 0.003%

    No Known Activations