© 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. 117823
    Prev
    Next
    INDEX
    Explanations

    immune mediated and metabolic disorders

    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
     वस्तुओं
    -0.06
     gesamten
    -0.06
    ไอ
    -0.06
     வாய்ப்ப
    -0.06
    အနေ
    -0.06
    entor
    -0.06
     સમગ્ર
    -0.06
     Qatar
    -0.05
    égard
    -0.05
    Inet
    -0.05
    POSITIVE LOGITS
     Locals
    0.08
    土地
    0.07
     haver
    0.07
     hå
    0.07
     Soil
    0.06
     soil
    0.06
     Local
    0.06
    地元
    0.06
     땅
    0.06
     local
    0.06
    Activations Density 0.085%

    No Known Activations