© 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. 117564
    Prev
    Next
    INDEX
    Explanations

    spores, hamuli, proglottids, coccobacillary, sophomore

    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
     někter
    -0.06
    农村
    -0.06
     jūs
    -0.06
     rufis
    -0.06
     частично
    -0.06
     некоторых
    -0.06
    ấu
    -0.06
    eleri
    -0.06
     niektórych
    -0.06
     você
    -0.06
    POSITIVE LOGITS
     produced
    0.07
    普
    0.06
     그래서
    0.06
     confidence
    0.06
    Produced
    0.06
     this
    0.05
    溶液
    0.05
     Produced
    0.05
     แห่ง
    0.05
    Crow
    0.05
    Activations Density 0.005%

    No Known Activations