© 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. 128938
    Prev
    Next
    INDEX
    Explanations

    inviting us

    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
     ใช้
    -0.07
     hopes
    -0.07
    ,..
    -0.06
    setValue
    -0.06
     steak
    -0.06
    ,...
    -0.06
    には
    -0.06
     tenía
    -0.06
     tinha
    -0.06
     είχε
    -0.06
    POSITIVE LOGITS
     silently
    0.07
     através
    0.06
     inquisitive
    0.06
     quietly
    0.06
    गुज
    0.06
     توسط
    0.06
     lentamente
    0.06
     बल
    0.06
     través
    0.06
     jouer
    0.05
    Activations Density 0.014%

    No Known Activations