© 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. 128601
    Prev
    Next
    INDEX
    Explanations

    Curtis Reid

    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
     Balancing
    -0.07
     when
    -0.07
     إذا
    -0.06
     incorrectly
    -0.06
    如果
    -0.06
     balancing
    -0.06
    balancing
    -0.06
     if
    -0.06
    önig
    -0.06
    តុ
    -0.06
    POSITIVE LOGITS
     वाले
    0.07
     będzie
    0.06
    那麼
    0.06
    扱い
    0.06
     लिंक
    0.06
     these
    0.06
     będ
    0.06
     также
    0.06
    ುತ್ತವೆ
    0.06
     menjadi
    0.06
    Activations Density 0.002%

    No Known Activations