© 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. 116636
    Prev
    Next
    INDEX
    Explanations

    like so:

    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
     다음과
    -0.07
    တွေ့
    -0.06
    állítás
    -0.06
     可
    -0.06
     ご
    -0.06
     在
    -0.06
    ([
    -0.06
     चाहते
    -0.06
     informal
    -0.06
    どんどん
    -0.06
    POSITIVE LOGITS
    ⚔
    0.06
     eigenen
    0.06
    ,?
    0.06
     उपकरणों
    0.06
    😎
    0.06
     irrig
    0.06
     oder
    0.06
     manchmal
    0.06
     ?!
    0.06
     😎
    0.05
    Activations Density 0.020%

    No Known Activations