© 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. 129681
    Prev
    Next
    INDEX
    Explanations

    right ventricle

    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
     unter
    -0.07
    原来
    -0.07
     onder
    -0.07
     গতকাল
    -0.07
     නව
    -0.06
     hagas
    -0.06
     tuleb
    -0.06
     inteligente
    -0.06
     neuen
    -0.06
     formulae
    -0.06
    POSITIVE LOGITS
     जिल्
    0.06
    Border
    0.06
    🏠
    0.06
    heny
    0.06
     questions
    0.05
     tries
    0.05
    questions
    0.05
    वेश
    0.05
     Havre
    0.05
    Boundary
    0.05
    Activations Density 0.005%

    No Known Activations