© 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. 120070
    Prev
    Next
    INDEX
    Explanations

    symmetric group, Sym, S_n, S3

    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
     uniformed
    -0.06
     итоге
    -0.06
    restassured
    -0.05
     periodista
    -0.05
     Communist
    -0.05
     ulike
    -0.05
     predictably
    -0.05
     déjà
    -0.05
     spectators
    -0.05
     desir
    -0.05
    POSITIVE LOGITS
    Written
    0.07
    윗
    0.06
     détecter
    0.06
     विस्फोटक
    0.06
     প্রকল্প
    0.06
     michael
    0.06
     workflows
    0.06
    ♝
    0.06
    அத
    0.06
     マルチ
    0.06
    Activations Density 0.004%

    No Known Activations