© 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. 129254
    Prev
    Next
    INDEX
    Explanations

    number of bathrooms

    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
     beiden
    -0.06
     augmented
    -0.06
     другой
    -0.06
     pili
    -0.06
    拍照
    -0.06
    もない
    -0.05
    谲
    -0.05
     প্রশ্নের
    -0.05
     சுதந்திர
    -0.05
    POSITIVE LOGITS
     खुद
    0.07
     czasie
    0.06
    direct
    0.06
    Different
    0.06
     neurons
    0.06
    कभी
    0.06
     aquelas
    0.06
    瞧
    0.06
    အချိန်
    0.06
    different
    0.05
    Activations Density 0.001%

    No Known Activations