© 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. 129518
    Prev
    Next
    INDEX
    Explanations

    code, technical terms, or specific sequences

    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
     keepsake
    -0.06
     encourages
    -0.06
     composition
    -0.06
     dopo
    -0.06
     complete
    -0.06
     deceased
    -0.06
     encouraged
    -0.06
    ierte
    -0.06
     made
    -0.06
     quotidienne
    -0.06
    POSITIVE LOGITS
     search
    0.07
    Vision
    0.07
     Vision
    0.07
     номер
    0.07
    空调
    0.07
    ६
    0.06
     Panel
    0.06
    問題を
    0.06
     petición
    0.06
     búsqueda
    0.06
    Activations Density 0.009%

    No Known Activations