© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128465
    Prev
    Next
    INDEX
    Explanations

    brackets, braces, math, code

    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
     diğer
    -0.07
     algunas
    -0.06
     beberapa
    -0.06
     algumas
    -0.06
     países
    -0.06
     інших
    -0.06
     dimana
    -0.06
    条件下
    -0.06
     tùy
    -0.06
     bats
    -0.06
    POSITIVE LOGITS
     consecrated
    0.06
     வித்திய
    0.06
     minimalistic
    0.06
     unmistak
    0.06
     риск
    0.06
     semicircle
    0.06
    aciju
    0.06
     മിക
    0.06
     sloppy
    0.05
     shockingly
    0.05
    Activations Density 0.001%

    No Known Activations