© 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. 129928
    Prev
    Next
    INDEX
    Explanations

    xml or configuration

    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
     بحيث
    -0.06
     பொதுவாக
    -0.06
    цах
    -0.06
     โดย
    -0.06
    ၶ
    -0.06
    زمانہ
    -0.06
     generalmente
    -0.06
     حيث
    -0.06
     commemoration
    -0.06
     genellikle
    -0.06
    POSITIVE LOGITS
     to
    0.07
     for
    0.06
    करिता
    0.06
    障
    0.06
    posts
    0.06
     goede
    0.06
     adequate
    0.06
    脊
    0.06
     Auth
    0.06
    mathfrak
    0.06
    Activations Density 0.002%

    No Known Activations