© 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. 128580
    Prev
    Next
    INDEX
    Explanations

    dimensions expressed by x

    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
    _="
    -0.06
     объеди
    -0.06
     весе
    -0.06
     bilden
    -0.06
     assistência
    -0.06
     garden
    -0.06
    して
    -0.06
    簷
    -0.05
     trailing
    -0.05
    好吧
    -0.05
    POSITIVE LOGITS
     અથવા
    0.06
     analyzing
    0.06
     demandé
    0.06
     này
    0.06
     анали
    0.06
     Prof
    0.06
     looking
    0.06
    avond
    0.06
    เอง
    0.06
    美国
    0.06
    Activations Density 0.002%

    No Known Activations