© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119098
    Prev
    Next
    INDEX
    Explanations

    understand

    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
    を
    -0.08
    它
    -0.07
    の
    -0.07
    それを
    -0.07
     в
    -0.06
     धा
    -0.06
    累计
    -0.06
    代表
    -0.06
     siempre
    -0.06
    ijski
    -0.06
    POSITIVE LOGITS
     results
    0.07
    成果
    0.06
    NO
    0.06
     resulted
    0.06
    ارج
    0.06
    相同
    0.06
     leads
    0.06
    ଫ
    0.06
     reclaimed
    0.06
     tends
    0.06
    Activations Density 0.001%

    No Known Activations