© 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. 120077
    Prev
    Next
    INDEX
    Explanations

    views and times

    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
    無法
    -0.07
     চালাতে
    -0.07
     incapable
    -0.06
     various
    -0.06
    不能
    -0.06
     jednego
    -0.06
     diversas
    -0.06
     várias
    -0.06
     aviones
    -0.06
     no
    -0.06
    POSITIVE LOGITS
     functions
    0.06
    尽管
    0.06
    Despite
    0.06
    Although
    0.06
     mentre
    0.06
    しながら
    0.06
     stairs
    0.06
     While
    0.06
     has
    0.06
     take
    0.06
    Activations Density 0.001%

    No Known Activations