© 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. 130036
    Prev
    Next
    INDEX
    Explanations

    reset button

    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
    続けて
    -0.06
    早已
    -0.06
     मैक्स
    -0.06
    Non
    -0.06
    Laser
    -0.06
     জানিয়েছেন
    -0.05
     ضمان
    -0.05
    非
    -0.05
     sappiamo
    -0.05
     शिला
    -0.05
    POSITIVE LOGITS
     अलग
    0.07
    影響
    0.06
     dalam
    0.06
     evokes
    0.06
     in
    0.06
     পালন
    0.06
     cercle
    0.06
     cela
    0.06
    _='
    0.06
     повлия
    0.06
    Activations Density 0.001%

    No Known Activations