© 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. 129563
    Prev
    Next
    INDEX
    Explanations

    epilepsy and outflow tract

    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
     synced
    -0.07
     (:
    -0.06
     subsequence
    -0.06
     синх
    -0.06
     photosynthesis
    -0.06
     COMPLET
    -0.06
     Minsk
    -0.06
    তনে
    -0.06
     monologue
    -0.06
     during
    -0.06
    POSITIVE LOGITS
     are
    0.07
     has
    0.06
    低的
    0.06
     कम
    0.06
     keamanan
    0.06
     International
    0.06
    usb
    0.06
    arid
    0.06
    Western
    0.06
    扱い
    0.06
    Activations Density 0.004%

    No Known Activations