© 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. 120061
    Prev
    Next
    INDEX
    Explanations

    calendars, AC, video sources, catalogues

    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
     सर्वप्रथम
    -0.06
    <eos>
    -0.06
     ſ
    -0.06
     expressed
    -0.06
     прида
    -0.06
     এলে
    -0.06
     establishing
    -0.06
     удержи
    -0.06
    This
    -0.06
    stability
    -0.06
    POSITIVE LOGITS
     ازاي
    0.07
     Miller
    0.06
    ajā
    0.06
     Robotic
    0.06
     있었다
    0.06
     catalogues
    0.06
    侗
    0.06
     toki
    0.06
     how
    0.06
     AUTO
    0.06
    Activations Density 0.001%

    No Known Activations