© 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. 116893
    Prev
    Next
    INDEX
    Explanations

    health conditions and remedies

    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
    ēi
    -0.06
     our
    -0.06
    increase
    -0.06
    捜
    -0.06
     creation
    -0.06
     voltages
    -0.06
    耐心
    -0.06
     motives
    -0.06
    推进
    -0.06
     méthod
    -0.06
    POSITIVE LOGITS
     групи
    0.06
     아무
    0.06
    和其他
    0.06
     какие
    0.06
     سمیت
    0.06
    taa
    0.06
     regionally
    0.06
    その他
    0.06
     King
    0.06
     よ
    0.06
    Activations Density 0.004%

    No Known Activations