© 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. 119793
    Prev
    Next
    INDEX
    Explanations

    import javax, the Mattson, in some, new observations

    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
    maximum
    -0.06
     exposition
    -0.06
    regions
    -0.06
     कंस
    -0.06
     areas
    -0.06
     കേന്ദ്ര
    -0.06
     Zoo
    -0.06
     regions
    -0.06
    both
    -0.05
    Both
    -0.05
    POSITIVE LOGITS
     помощи
    0.07
     ಸಹಾಯ
    0.07
     একত্রে
    0.07
    যোগে
    0.06
     segí
    0.06
     pomoc
    0.06
     helping
    0.06
     ولكن
    0.06
     แต่
    0.06
     hỗ
    0.06
    Activations Density 0.002%

    No Known Activations