© 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. 129310
    Prev
    Next
    INDEX
    Explanations

    medical care decisions

    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
     Disney
    -0.05
     GROUP
    -0.05
    esten
    -0.05
    売
    -0.05
     muro
    -0.05
     pous
    -0.05
     záv
    -0.05
     защи
    -0.05
    curity
    -0.05
     volume
    -0.05
    POSITIVE LOGITS
     ತೆಗೆದುಕೊಳ್ಳ
    0.07
     motores
    0.07
    <0xA6>
    0.06
     테스트
    0.06
     tìm
    0.06
     искать
    0.06
     exe
    0.06
     prazo
    0.06
    に行く
    0.06
     wybrać
    0.06
    Activations Density 0.052%

    No Known Activations