© 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. 130372
    Prev
    Next
    INDEX
    Explanations

    approximatley after measurement

    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
     new
    -0.07
    new
    -0.06
     LABEL
    -0.06
     NEW
    -0.06
     অমন
    -0.05
     उत्पा
    -0.05
    inska
    -0.05
    func
    -0.05
    烹
    -0.05
     beautiful
    -0.05
    POSITIVE LOGITS
     secretive
    0.07
    といった
    0.07
    等的
    0.06
    老师
    0.06
     aquí
    0.06
    ించే
    0.06
    ގެ
    0.06
     ہر
    0.06
     நாள்
    0.06
    😢
    0.06
    Activations Density 0.008%

    No Known Activations