© 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. 120027
    Prev
    Next
    INDEX
    Explanations

    Playboy, swim, PHP code, proposals

    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
     kēia
    -0.07
     apprendre
    -0.07
     giorno
    -0.07
     يمكن
    -0.06
    를
    -0.06
    跨境
    -0.06
     दिवशी
    -0.06
     jour
    -0.06
    seconds
    -0.06
    স্প
    -0.06
    POSITIVE LOGITS
    Constitution
    0.06
     cudd
    0.06
     Constitution
    0.06
    后续
    0.06
     물
    0.06
     estructural
    0.06
     संशोध
    0.06
    🐭
    0.06
     millennials
    0.06
    Ball
    0.06
    Activations Density 0.003%

    No Known Activations