© 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. 119665
    Prev
    Next
    INDEX
    Explanations

    reserved words and syntax

    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
    Erro
    -0.07
    İlk
    -0.06
     JVM
    -0.06
     achievements
    -0.06
    泠
    -0.06
     tyl
    -0.06
     microbiological
    -0.06
     infert
    -0.06
    inputType
    -0.06
    🚍
    -0.06
    POSITIVE LOGITS
     from
    0.07
     ডি
    0.06
     C
    0.06
    、
    0.06
    Or
    0.05
    рь
    0.05
    an
    0.05
     や
    0.05
     consider
    0.05
    これから
    0.05
    Activations Density 0.002%

    No Known Activations