© 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. 129569
    Prev
    Next
    INDEX
    Explanations

    leading causes or reasons

    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
     neurotrans
    -0.07
     기존
    -0.07
    ப்பூர்
    -0.07
     உள்ளிட்ட
    -0.06
     присут
    -0.06
     descre
    -0.06
    這些
    -0.06
    Currently
    -0.06
    scorpion
    -0.06
     tieto
    -0.06
    POSITIVE LOGITS
     Health
    0.08
     carpentry
    0.07
     health
    0.07
     ceinture
    0.07
     emphas
    0.06
     Gesundheit
    0.06
     plumber
    0.06
     Furniture
    0.06
     GST
    0.06
    四
    0.06
    Activations Density 0.010%

    No Known Activations