© 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. 119029
    Prev
    Next
    INDEX
    Explanations

    extract &

    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
     mixing
    -0.09
    แบ่ง
    -0.07
    定时
    -0.07
    mixing
    -0.07
    Mixing
    -0.06
    殒
    -0.06
    服用
    -0.06
     spiced
    -0.06
    समय
    -0.06
     Mixing
    -0.06
    POSITIVE LOGITS
     właści
    0.06
     θε
    0.06
    ابط
    0.05
    opedic
    0.05
     सहानु
    0.05
     generalizes
    0.05
    ွေ
    0.05
     मानवीय
    0.05
     শাম
    0.05
     lawyer
    0.05
    Activations Density 0.007%

    No Known Activations