© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130279
    Prev
    Next
    INDEX
    Explanations

    job titles and associated roles

    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
     speziell
    -0.07
     specialists
    -0.07
    专家
    -0.07
    协助
    -0.07
    专门
    -0.07
    专业
    -0.07
     विशेषज्ञ
    -0.07
    専門
    -0.07
     specjal
    -0.07
     متخصص
    -0.07
    POSITIVE LOGITS
     two
    0.07
     the
    0.06
     forget
    0.06
     বাংলাদেশ
    0.06
     changement
    0.06
    ité
    0.06
    ăț
    0.06
     Samsung
    0.06
    ặp
    0.05
    قتصاد
    0.05
    Activations Density 0.017%

    No Known Activations