© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119711
    Prev
    Next
    INDEX
    Explanations

    health assessments online

    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
     adjustments
    -0.07
     monitoring
    -0.06
     régi
    -0.06
     modific
    -0.06
    年
    -0.06
     their
    -0.06
    ัญหา
    -0.06
     uprav
    -0.06
    调整
    -0.06
     cess
    -0.06
    POSITIVE LOGITS
    申込
    0.07
     desired
    0.06
    方便
    0.06
     guilt
    0.06
     willingness
    0.06
     желание
    0.06
     motivations
    0.06
    之間
    0.06
     உடன
    0.05
     connotations
    0.05
    Activations Density 0.001%

    No Known Activations