© 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. 119926
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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
    ৪৩
    -0.06
    colorful
    -0.06
     rocky
    -0.06
     වශයෙන්
    -0.05
    all
    -0.05
    tu
    -0.05
    点は
    -0.05
     Alltag
    -0.05
     forskellige
    -0.05
    色的
    -0.05
    POSITIVE LOGITS
     WILL
    0.07
     requested
    0.07
     durante
    0.06
     diretamente
    0.06
     permette
    0.06
    ֡
    0.06
    采用
    0.06
     permet
    0.06
    意大利
    0.06
     Nuestros
    0.06
    Activations Density 0.017%

    No Known Activations