© 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. 118174
    Prev
    Next
    INDEX
    Explanations

    needed or required

    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
    சித்த
    -0.06
    あり
    -0.06
     categories
    -0.06
     अडचणी
    -0.06
     indicative
    -0.06
     amigo
    -0.06
     brackets
    -0.06
     வந்த
    -0.06
    should
    -0.06
    REAL
    -0.06
    POSITIVE LOGITS
     all
    0.06
     education
    0.06
     quizá
    0.06
    Ī
    0.06
     ডেপুটি
    0.06
     perhaps
    0.06
    ransition
    0.05
    到一个
    0.05
    ikuwa
    0.05
    IJ
    0.05
    Activations Density 0.008%

    No Known Activations