© 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. 116526
    Prev
    Next
    INDEX
    Explanations

    stadiums and sports matches

    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
    変化
    -0.07
     fragmented
    -0.06
    --(
    -0.06
     merger
    -0.06
    各
    -0.06
     mergers
    -0.06
    劦
    -0.06
    それぞれ
    -0.06
     pursuit
    -0.06
     EXEMPLARY
    -0.06
    POSITIVE LOGITS
     use
    0.08
     Use
    0.07
    use
    0.07
     иной
    0.06
     uso
    0.06
     utiliser
    0.06
    Use
    0.06
    practical
    0.06
     علاوه
    0.06
     onwards
    0.06
    Activations Density 0.008%

    No Known Activations