© 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. 116761
    Prev
    Next
    INDEX
    Explanations

    surgical or medical studies

    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
     임
    -0.08
    奥运
    -0.08
     मृत्यु
    -0.07
     graphics
    -0.06
     Ф
    -0.06
     गर्भावस्था
    -0.06
     seperti
    -0.06
     veröffentlicht
    -0.06
    學院
    -0.06
    员工
    -0.06
    POSITIVE LOGITS
    Join
    0.05
    ши
    0.05
     bygone
    0.05
    ไต
    0.05
     allotted
    0.05
    lec
    0.05
     mengungkap
    0.05
    ’।
    0.05
     Join
    0.05
    issant
    0.05
    Activations Density 0.016%

    No Known Activations