© 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. 118570
    Prev
    Next
    INDEX
    Explanations

    SAI, DAI

    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
     इस
    -0.07
    ക്കുറിച്ച്
    -0.07
     ৫
    -0.07
    終わ
    -0.07
     김
    -0.07
     the
    -0.06
     आजकल
    -0.06
     each
    -0.06
     this
    -0.06
     herkes
    -0.06
    POSITIVE LOGITS
     معمولی
    0.06
     اثر
    0.06
    è
    0.06
     मोटे
    0.06
    Various
    0.06
     несколь
    0.05
    actual
    0.05
    will
    0.05
    несла
    0.05
    [...]
    0.05
    Activations Density 0.001%

    No Known Activations