© 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. 116446
    Prev
    Next
    INDEX
    Explanations

    orthodontics and dental care

    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
    Visitation
    -0.06
     گروپ
    -0.06
     group
    -0.06
     insights
    -0.06
     समूह
    -0.06
     مشکل
    -0.06
     osób
    -0.06
    个小时
    -0.06
     today
    -0.06
     roundup
    -0.06
    POSITIVE LOGITS
     शेवट
    0.07
     фина
    0.06
     proceso
    0.06
    慢慢
    0.06
    大致
    0.06
     süreç
    0.06
     culminated
    0.06
     etapas
    0.06
     Dream
    0.06
    反复
    0.06
    Activations Density 0.011%

    No Known Activations