© 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. 117243
    Prev
    Next
    INDEX
    Explanations

    percentage calculation and usage

    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
     основного
    -0.07
    ંત
    -0.07
    将
    -0.06
    主要的
    -0.06
    national
    -0.06
     Moreover
    -0.06
     اصلی
    -0.06
     કરાવ
    -0.06
     Simply
    -0.06
    parents
    -0.06
    POSITIVE LOGITS
    ๋า
    0.06
     which
    0.06
     التي
    0.06
    ទេ
    0.06
     eccentric
    0.06
    neſs
    0.06
     dois
    0.06
    körper
    0.06
    兩人
    0.06
     koje
    0.06
    Activations Density 0.034%

    No Known Activations