© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129802
    Prev
    Next
    INDEX
    Explanations

    sales, Junior, American, enable, Update

    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
     corrispond
    -0.06
    fread
    -0.06
    ೇವ
    -0.06
     correspondant
    -0.06
    hasht
    -0.06
     الزام
    -0.06
     femora
    -0.05
     جیت
    -0.05
     አይ
    -0.05
    䏲
    -0.05
    POSITIVE LOGITS
     Grande
    0.07
     за
    0.07
     لكن
    0.07
    Truly
    0.06
    Another
    0.06
     Avalanche
    0.06
    another
    0.06
    한다는
    0.06
     আরেকটি
    0.06
    Placed
    0.06
    Activations Density 0.001%

    No Known Activations