© 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. 119641
    Prev
    Next
    INDEX
    Explanations

    SET, ON, OFF, delimiter, import

    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
     კი
    -0.06
     رشد
    -0.06
    ática
    -0.06
    arında
    -0.06
     critics
    -0.06
    nier
    -0.06
     गिफ्ट
    -0.06
     essa
    -0.06
    alé
    -0.06
     angla
    -0.06
    POSITIVE LOGITS
     เพื่อ
    0.07
    Un
    0.06
     ដើម្បី
    0.06
     для
    0.06
    确认
    0.06
     a
    0.06
    On
    0.06
    為了
    0.06
    I
    0.06
     চমৎকার
    0.05
    Activations Density 0.001%

    No Known Activations