© 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. 128930
    Prev
    Next
    INDEX
    Explanations

    multi-RAT capability, multi-chip packages, tandem organocatalysis

    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
    合う
    -0.06
     взаимодействия
    -0.06
     взаимодей
    -0.06
     इज़
    -0.06
    йо
    -0.06
     interplay
    -0.06
     dimanche
    -0.06
     clandestine
    -0.06
    Hasta
    -0.06
    Until
    -0.06
    POSITIVE LOGITS
     aparato
    0.06
     στη
    0.06
     توسط
    0.06
    ?),
    0.06
     not
    0.06
     target
    0.06
     costly
    0.06
     logements
    0.06
     truly
    0.06
     Exhaust
    0.06
    Activations Density 0.021%

    No Known Activations