© 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. 129194
    Prev
    Next
    INDEX
    Explanations

    pipeline, TransMountain, LNG, Event listener

    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
    bouquet
    -0.07
     بچه
    -0.06
     too
    -0.06
     子
    -0.06
     खूप
    -0.06
     너무
    -0.06
     بچوں
    -0.06
     gyermek
    -0.06
    PosX
    -0.06
    火山
    -0.06
    POSITIVE LOGITS
    ான
    0.06
     പറഞ്ഞു
    0.06
    migrations
    0.06
     Ecosystem
    0.06
     पै
    0.06
     migrations
    0.06
    的历史
    0.06
     Adu
    0.06
     countries
    0.06
    лка
    0.06
    Activations Density 0.006%

    No Known Activations