© 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. 130394
    Prev
    Next
    INDEX
    Explanations

    features

    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
    ito
    -0.06
     vitally
    -0.06
    List
    -0.05
    RA
    -0.05
     уника
    -0.05
    MAX
    -0.05
     (*
    -0.05
     स्पेश
    -0.05
     gonna
    -0.05
    Middleware
    -0.05
    POSITIVE LOGITS
     zumindest
    0.07
     सभी
    0.07
     Although
    0.06
    begin
    0.06
     beginnen
    0.06
     Đáp
    0.06
     хотя
    0.06
     a
    0.06
    اصيل
    0.06
     todas
    0.06
    Activations Density 0.001%

    No Known Activations