© 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. 119302
    Prev
    Next
    INDEX
    Explanations

    OUT

    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
     以
    -0.07
     開
    -0.06
     in
    -0.06
     开
    -0.06
    दों
    -0.06
     बल्लेबाज
    -0.06
    多种
    -0.06
    以
    -0.06
     kulttu
    -0.06
     इसे
    -0.06
    POSITIVE LOGITS
     நாங்கள்
    0.06
     distress
    0.06
     பாதிக்கிறது
    0.06
     কাজেই
    0.06
     seems
    0.06
     dependiendo
    0.06
    hees
    0.06
     espejo
    0.06
     explains
    0.06
     migrated
    0.05
    Activations Density 0.006%

    No Known Activations