© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130362
    Prev
    Next
    INDEX
    Explanations

    means or 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
     защото
    -0.07
     because
    -0.07
    法の
    -0.07
    している
    -0.07
     வால்பேப்ப
    -0.06
     Dollar
    -0.06
    porque
    -0.06
     ジャン
    -0.06
     لأنه
    -0.06
     deshalb
    -0.06
    POSITIVE LOGITS
     ,
    0.06
    non
    0.06
                                   
    0.06
     non
    0.06
     .
    0.06
    <strong>
    0.06
    Non
    0.05
     sammeln
    0.05
    you
    0.05
    HS
    0.05
    Activations Density 0.081%

    No Known Activations