© 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. 120143
    Prev
    Next
    INDEX
    Explanations

    surgical procedures and outcomes

    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
     suggestive
    -0.08
     conclud
    -0.07
     suggesting
    -0.07
     sugest
    -0.07
     говорят
    -0.07
     suger
    -0.07
     approachable
    -0.07
     meaningfully
    -0.07
     ಅವನು
    -0.07
     तैयार
    -0.07
    POSITIVE LOGITS
     마
    0.06
    ुरू
    0.06
    kel
    0.05
     mete
    0.05
    和
    0.05
     पॉलिट
    0.05
     जवाब
    0.05
    Fun
    0.05
     अबा
    0.05
    ዋ
    0.05
    Activations Density 0.009%

    No Known Activations