© 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. 128606
    Prev
    Next
    INDEX
    Explanations

    numbers and 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
     и
    -0.06
    CAG
    -0.06
     και
    -0.06
    แต่
    -0.06
     compose
    -0.06
     Cebu
    -0.06
    АТ
    -0.06
    但是
    -0.06
    SIGN
    -0.06
    ière
    -0.06
    POSITIVE LOGITS
     thuộc
    0.07
     usable
    0.06
     detailed
    0.06
    rneğin
    0.06
     elicit
    0.06
     blatantly
    0.06
     of
    0.06
    ="")
    0.06
     often
    0.06
     meticulous
    0.06
    Activations Density 0.019%

    No Known Activations