© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129473
    Prev
    Next
    INDEX
    Explanations

    constructor or method calls

    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
     when
    -0.06
     When
    -0.06
    켓
    -0.06
     विभा
    -0.06
     утро
    -0.06
     bild
    -0.06
    evice
    -0.06
    When
    -0.06
     quando
    -0.06
    imiz
    -0.06
    POSITIVE LOGITS
     جدید
    0.07
     nuove
    0.06
     new
    0.06
    こういう
    0.06
     mới
    0.06
     νέα
    0.06
     impunity
    0.06
     புதிய
    0.06
     estacion
    0.06
     पर्याप्त
    0.06
    Activations Density 0.001%

    No Known Activations