© 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. 119654
    Prev
    Next
    INDEX
    Explanations

    import statements in code

    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
     hő
    -0.07
     interesados
    -0.06
     बवाल
    -0.06
     парази
    -0.06
     ก่อน
    -0.06
     may
    -0.06
    단체
    -0.06
    ॉस
    -0.06
    Denmark
    -0.06
    뵐
    -0.06
    POSITIVE LOGITS
     Enrich
    0.07
    íu
    0.05
     HARD
    0.05
     jaoks
    0.05
    substring
    0.05
    life
    0.05
     Elast
    0.05
     querc
    0.05
    uir
    0.05
    だけ
    0.05
    Activations Density 0.001%

    No Known Activations