© 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. 120219
    Prev
    Next
    INDEX
    Explanations

    digit or mathematical values

    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
     valuation
    -0.07
     Levels
    -0.07
     отдельные
    -0.07
     questi
    -0.07
     conceptions
    -0.06
    最为
    -0.06
     yapılan
    -0.06
    omeness
    -0.06
     về
    -0.06
     hebben
    -0.06
    POSITIVE LOGITS
     nút
    0.06
     двух
    0.05
     Endless
    0.05
     চার
    0.05
     görüntü
    0.05
    ಬ್ಬ
    0.05
     notorious
    0.05
     they
    0.05
    hurst
    0.05
    ায়ক
    0.05
    Activations Density 0.003%

    No Known Activations