© 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. 116449
    Prev
    Next
    INDEX
    Explanations

    dates and time

    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
     is
    -0.06
     or
    -0.06
    ↵↵
    -0.06
     be
    -0.06
     $.
    -0.06
     
    -0.05
     $
    -0.05
     Эта
    -0.05
     use
    -0.05
     अक्सर
    -0.05
    POSITIVE LOGITS
     ಹಾಗೂ
    0.08
     và
    0.08
     ಮತ್ತು
    0.08
    ność
    0.07
     एवं
    0.07
     khi
    0.07
     bepaalde
    0.07
     των
    0.07
     மற்றும்
    0.07
     morning
    0.06
    Activations Density 0.015%

    No Known Activations