© 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. 120103
    Prev
    Next
    INDEX
    Explanations

    descriptions and metadata

    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
     incredible
    -0.06
     (
    -0.06
    Envelope
    -0.06
     एसएमएस
    -0.06
     (~
    -0.06
     envelope
    -0.06
     किन्तु
    -0.06
     যুদ্ধে
    -0.06
     astounding
    -0.06
    .(
    -0.06
    POSITIVE LOGITS
     botched
    0.07
     такого
    0.06
     මේ
    0.06
     здійс
    0.06
     तकरीबन
    0.06
     stessa
    0.06
     శరీర
    0.06
     forthcoming
    0.06
     there
    0.05
     商品
    0.05
    Activations Density 0.001%

    No Known Activations