© 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. 119375
    Prev
    Next
    INDEX
    Explanations

    moving image

    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
     perfe
    -0.06
     увеличения
    -0.06
     README
    -0.06
    与之
    -0.06
     ประกอบ
    -0.06
     సమావేశ
    -0.06
     univariate
    -0.05
     Kunst
    -0.05
    quer
    -0.05
    上の
    -0.05
    POSITIVE LOGITS
     county
    0.07
     പൊതു
    0.07
     зробити
    0.06
    ardom
    0.06
    ន្ត
    0.06
     பொது
    0.06
     generale
    0.06
     populate
    0.06
     County
    0.06
     generally
    0.06
    Activations Density 0.005%

    No Known Activations