© 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. 116438
    Prev
    Next
    INDEX
    Explanations

    SL, email, Zarosliak

    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
     memeriksa
    -0.07
     Smartphone
    -0.06
     trusted
    -0.06
     memastikan
    -0.06
    获取
    -0.06
     optimal
    -0.06
     obtiene
    -0.06
    高铁
    -0.06
    高效
    -0.06
     evidente
    -0.06
    POSITIVE LOGITS
     rulemaking
    0.06
     habitable
    0.06
     mingling
    0.06
    physics
    0.06
     conversations
    0.06
     negotiations
    0.06
     simulates
    0.06
     ازد
    0.06
     metaverse
    0.06
     EXCHANGE
    0.06
    Activations Density 0.005%

    No Known Activations