© 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. 116594
    Prev
    Next
    INDEX
    Explanations

    CW-complex, potentials, Richtweg

    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
    两个
    -0.06
     medzi
    -0.06
     между
    -0.06
     tussen
    -0.06
     between
    -0.06
    between
    -0.06
     frustration
    -0.06
     two
    -0.06
     পত্রিকাটি
    -0.06
    Non
    -0.06
    POSITIVE LOGITS
    是有
    0.07
     reiniciar
    0.06
     sinnv
    0.06
     ошибка
    0.06
    hierarchy
    0.06
     조금
    0.06
     Wiring
    0.06
     vehículo
    0.06
     없다
    0.06
     superfici
    0.05
    Activations Density 0.001%

    No Known Activations