© 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. 117384
    Prev
    Next
    INDEX
    Explanations

    Options for specific keywords

    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
    等の
    -0.07
    等的
    -0.07
     adicion
    -0.06
     various
    -0.06
    などで
    -0.06
    などに
    -0.06
    などの
    -0.06
     등의
    -0.06
     mischief
    -0.06
     ٹیم
    -0.06
    POSITIVE LOGITS
     Daarna
    0.06
     multiplies
    0.06
    కాశ
    0.06
    prised
    0.06
     घेतल्या
    0.05
    檗
    0.05
    ುದು
    0.05
     ECU
    0.05
    lapping
    0.05
     și
    0.05
    Activations Density 0.009%

    No Known Activations