© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117924
    Prev
    Next
    INDEX
    Explanations

    healthy volunteers

    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
     Sammlung
    -0.07
     speriment
    -0.07
     numerosi
    -0.06
     ballroom
    -0.06
     demonstrates
    -0.06
    Procedure
    -0.06
    其他的
    -0.06
     መሳሪያ
    -0.06
     ዘዴ
    -0.06
     adorable
    -0.06
    POSITIVE LOGITS
     começ
    0.06
    řez
    0.06
     কন্
    0.06
    Simply
    0.06
    ंपासून
    0.06
    าค
    0.06
    хран
    0.06
    new
    0.06
     References
    0.06
     preço
    0.06
    Activations Density 0.007%

    No Known Activations