© 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. 117493
    Prev
    Next
    INDEX
    Explanations

    survey, information, evaluation, placement

    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
     now
    -0.07
     теперь
    -0.07
     ಮನೆಯ
    -0.07
     போன்றவற்ற
    -0.07
     then
    -0.06
     pertenc
    -0.06
     Now
    -0.06
     پھر
    -0.06
     воздуха
    -0.06
     Respiratory
    -0.06
    POSITIVE LOGITS
    過程中
    0.06
    Processed
    0.06
    Illus
    0.06
    誹
    0.06
     photographer
    0.06
    过程中
    0.06
     अनुच्छेद
    0.06
     actionable
    0.06
    摄影
    0.06
     सेक्सी
    0.06
    Activations Density 0.004%

    No Known Activations