© 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. 120333
    Prev
    Next
    INDEX
    Explanations

    render method

    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
     heady
    -0.07
     lado
    -0.07
     sloppy
    -0.07
     Здесь
    -0.07
     Hotline
    -0.06
     bogus
    -0.06
     শিগ
    -0.06
    智能化
    -0.06
     detect
    -0.06
     minib
    -0.06
    POSITIVE LOGITS
     pratique
    0.07
     gefragt
    0.06
     chín
    0.06
     Practical
    0.06
     prakt
    0.06
     права
    0.06
    wives
    0.06
     Separate
    0.06
     praktische
    0.05
     practical
    0.05
    Activations Density 0.001%

    No Known Activations