© 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. 119854
    Prev
    Next
    INDEX
    Explanations

    code imports and declarations

    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
    जर
    -0.07
     কিংবা
    -0.06
     ।
    -0.06
     zie
    -0.06
    サイズの
    -0.06
     Some
    -0.06
    หรือ
    -0.06
     सामान्य
    -0.06
    রাসের
    -0.06
     ।*
    -0.06
    POSITIVE LOGITS
    elf
    0.06
     with
    0.06
    䒠
    0.05
     वस्तू
    0.05
    觓
    0.05
     främ
    0.05
    鿌
    0.05
    㭐
    0.05
    这
    0.05
    bios
    0.05
    Activations Density 0.002%

    No Known Activations