© 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. 128323
    Prev
    Next
    INDEX
    Explanations

    UTF-8

    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
    特定的
    -0.07
     bientôt
    -0.07
     പുതിയ
    -0.07
     extermin
    -0.07
    专属
    -0.06
     contemporary
    -0.06
     पात्र
    -0.06
     yeni
    -0.06
    Contemporary
    -0.06
     members
    -0.06
    POSITIVE LOGITS
     selles
    0.07
    RAN
    0.07
     যানবাহ
    0.06
     desarrollando
    0.06
     θε
    0.06
     utilizó
    0.06
    ielles
    0.06
     milliam
    0.06
    ός
    0.06
     vaccinate
    0.06
    Activations Density 0.002%

    No Known Activations