© 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. 128879
    Prev
    Next
    INDEX
    Explanations

    industrial, PC, USB, bridges

    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
     tener
    -0.07
     Tennessee
    -0.06
    Hence
    -0.06
    Different
    -0.06
     selbst
    -0.06
     YEARS
    -0.06
    ahas
    -0.06
    different
    -0.06
     Hence
    -0.06
    utives
    -0.06
    POSITIVE LOGITS
     (
    0.08
     currently
    0.07
    (
    0.07
    డ్
    0.06
     actualmente
    0.06
     PC
    0.05
    ድግዳ
    0.05
     поддержи
    0.05
    oló
    0.05
     पदार्थ
    0.05
    Activations Density 0.033%

    No Known Activations