© 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. 130416
    Prev
    Next
    INDEX
    Explanations

    Vim editor configurations

    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
    ；
    -0.07
    ؛
    -0.06
    在那里
    -0.06
     sitten
    -0.06
     uczest
    -0.06
    驽
    -0.06
     মুর্
    -0.06
     stream
    -0.06
    Initially
    -0.06
    ヨタ
    -0.06
    POSITIVE LOGITS
     explains
    0.07
     checkIf
    0.06
    global
    0.06
     glob
    0.06
     Heritage
    0.06
     Mourinho
    0.06
     cerebrospinal
    0.06
     international
    0.06
     knelt
    0.06
     global
    0.06
    Activations Density 0.009%

    No Known Activations