© 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. 117297
    Prev
    Next
    INDEX
    Explanations

    sewing and related crafts

    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
    antian
    -0.06
    onion
    -0.06
     lingue
    -0.06
     moieties
    -0.06
     плани
    -0.06
     từ
    -0.06
     consisting
    -0.06
    🥔
    -0.06
     bestaan
    -0.06
    dym
    -0.06
    POSITIVE LOGITS
     bénéf
    0.07
    Video
    0.06
    Specific
    0.06
     officielle
    0.06
     Owners
    0.06
     Contract
    0.06
     Kont
    0.06
     subparagraph
    0.06
    オーナー
    0.06
     ശാ
    0.06
    Activations Density 0.002%

    No Known Activations