© 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. 117434
    Prev
    Next
    INDEX
    Explanations

    mathematical and code symbols

    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
     συ
    -0.06
    न्
    -0.06
    ப்பர்
    -0.06
     си
    -0.06
     रीट
    -0.06
    riere
    -0.06
     Tind
    -0.06
     wharf
    -0.06
     क्वांट
    -0.06
    一样
    -0.06
    POSITIVE LOGITS
     various
    0.06
    筠
    0.06
     секунд
    0.06
    既存
    0.06
    quare
    0.06
     °
    0.06
     فرمان
    0.06
     Exponential
    0.06
     peças
    0.06
     Existing
    0.06
    Activations Density 0.003%

    No Known Activations