© 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. 119205
    Prev
    Next
    INDEX
    Explanations

    structural components (housing, body, frame)

    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
     gegenüber
    -0.07
     BEFORE
    -0.06
    WARN
    -0.06
     sebelum
    -0.06
    対
    -0.06
    ファッション
    -0.06
     Kunden
    -0.06
     before
    -0.06
     beforehand
    -0.06
    之前
    -0.06
    POSITIVE LOGITS
    ственном
    0.06
    primarily
    0.06
     primarily
    0.06
    נדי
    0.06
    bido
    0.06
     দুই
    0.06
    ENUM
    0.06
    涵盖
    0.05
     mici
    0.05
    embry
    0.05
    Activations Density 0.023%

    No Known Activations