© 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. 120089
    Prev
    Next
    INDEX
    Explanations

    other followed by a category

    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
    及び
    -0.06
    を使った
    -0.06
     Mystic
    -0.06
    에는
    -0.05
    ӯ
    -0.05
     hanem
    -0.05
    FAKE
    -0.05
     तथा
    -0.05
     oraz
    -0.05
    Summary
    -0.05
    POSITIVE LOGITS
     একইভাবে
    0.07
    pageNum
    0.07
    这两
    0.06
     обычно
    0.06
     both
    0.06
    However
    0.06
     acon
    0.06
     similarly
    0.06
    nemouth
    0.06
    similar
    0.06
    Activations Density 0.004%

    No Known Activations