© 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. 130177
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and sequences

    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
    Durante
    -0.06
    selection
    -0.06
     Uk
    -0.06
     Durante
    -0.06
     są
    -0.06
     durante
    -0.06
     tomography
    -0.06
    hong
    -0.06
     selection
    -0.06
     benar
    -0.06
    POSITIVE LOGITS
    再び
    0.07
     处理
    0.06
     ऐप्प
    0.06
     此
    0.06
     дома
    0.06
    Можно
    0.06
     ',',
    0.06
     Possible
    0.06
    再次
    0.05
     **
    0.05
    Activations Density 0.001%

    No Known Activations