© 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. 117819
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    强大的
    -0.06
     predominantly
    -0.06
     inexpensive
    -0.06
     बढ़ाने
    -0.06
     (
    -0.05
     what
    -0.05
     invariable
    -0.05
     cabelo
    -0.05
     mainly
    -0.05
     three
    -0.05
    POSITIVE LOGITS
     or
    0.07
     Eligible
    0.07
    Elig
    0.07
     образова
    0.06
    eligible
    0.06
     ज्वालामुखी
    0.06
     อีก
    0.06
    🔌
    0.06
     kvinn
    0.06
     whose
    0.06
    Activations Density 0.000%

    No Known Activations