© 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. 121063
    Prev
    Next
    INDEX
    Explanations

    motor neuron activation or denervation

    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
     toughness
    -0.07
     anabolic
    -0.07
    lifting
    -0.07
     LOADING
    -0.07
     muscle
    -0.07
     CrossFit
    -0.07
     ప్రస్తుతం
    -0.06
     Improve
    -0.06
    muscle
    -0.06
     Strength
    -0.06
    POSITIVE LOGITS
     Children
    0.07
     trickle
    0.06
    개의
    0.06
     children
    0.06
    个
    0.06
    getChildren
    0.06
     Infine
    0.06
     because
    0.06
    ӳ
    0.06
     erstes
    0.06
    Activations Density 0.046%

    No Known Activations