© 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. 129386
    Prev
    Next
    INDEX
    Explanations

    legal citations with volume numbers

    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
    bes
    -0.06
    roffen
    -0.06
    щая
    -0.06
     Militar
    -0.06
     microphone
    -0.06
     incidental
    -0.06
    仟
    -0.06
    inescent
    -0.06
    ススメ
    -0.06
     Owen
    -0.06
    POSITIVE LOGITS
    ',
    0.07
    ",
    0.06
    ,
    0.06
     hasn
    0.06
    ဳ
    0.06
    如
    0.06
     jamais
    0.06
     সমন্বয়
    0.05
     حاول
    0.05
    ′,
    0.05
    Activations Density 0.004%

    No Known Activations