© 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. 129064
    Prev
    Next
    INDEX
    Explanations

    question or "a" followed by a word

    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
     allowing
    -0.07
    ᓂ
    -0.07
     slid
    -0.06
     keeps
    -0.06
     తర్వాత
    -0.06
    深受
    -0.06
     convexes
    -0.06
     hanya
    -0.06
    allowing
    -0.06
    ቒ
    -0.06
    POSITIVE LOGITS
    /),
    0.06
     first
    0.06
     ঘুর
    0.05
     employees
    0.05
     দামে
    0.05
     gratis
    0.05
    ိုး
    0.05
    0.05
    ut
    0.05
    className
    0.05
    Activations Density 0.002%

    No Known Activations