© 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. 118946
    Prev
    Next
    INDEX
    Explanations

    size parameter

    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
     takich
    -0.07
     tych
    -0.06
     unor
    -0.06
     મુજબ
    -0.06
     таких
    -0.05
     طبق
    -0.05
    一次
    -0.05
    Yang
    -0.05
     قوت
    -0.05
     Efter
    -0.05
    POSITIVE LOGITS
    विरुद्ध
    0.06
    成為
    0.06
     aspects
    0.06
     আসিয়া
    0.06
     criticisms
    0.06
    omicron
    0.06
     ¿
    0.06
    മല്ല
    0.06
    就算是
    0.06
     eating
    0.06
    Activations Density 0.001%

    No Known Activations