© 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. 128625
    Prev
    Next
    INDEX
    Explanations

    order to

    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
     prevents
    -0.08
     khiến
    -0.08
     precludes
    -0.08
     allows
    -0.08
    使得
    -0.08
     ensures
    -0.08
     preclude
    -0.07
    确保
    -0.07
    ทำให้
    -0.07
     ensure
    -0.07
    POSITIVE LOGITS
     cả
    0.06
     номером
    0.06
     view
    0.06
    oq
    0.06
    Where
    0.06
    Если
    0.06
    ணர்
    0.06
    相关
    0.06
     où
    0.06
    OH
    0.06
    Activations Density 0.017%

    No Known Activations