© 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. 119637
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Can you"

    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
     Ihrem
    -0.06
    研究所
    -0.06
    frames
    -0.06
    PCs
    -0.05
     يساوي
    -0.05
    Parm
    -0.05
     vient
    -0.05
    直播
    -0.05
     workstations
    -0.05
     металла
    -0.05
    POSITIVE LOGITS
    roman
    0.07
     necessárias
    0.07
     imported
    0.06
    ándose
    0.06
     necessary
    0.06
     nomencl
    0.06
    wają
    0.06
     protruding
    0.06
     aspiring
    0.06
     He
    0.06
    Activations Density 0.002%

    No Known Activations