© 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. 116243
    Prev
    Next
    INDEX
    Explanations

    create AR

    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
    ığım
    -0.08
     linguagem
    -0.06
     Comenz
    -0.06
     sämt
    -0.06
     fugit
    -0.06
     tanned
    -0.06
     APIs
    -0.06
     recomendado
    -0.06
     linguaggio
    -0.06
    ഗ്ര
    -0.06
    POSITIVE LOGITS
     amateur
    0.07
     informal
    0.07
     informally
    0.06
    shared
    0.06
    喜
    0.06
     amateurs
    0.06
    ユーザ
    0.06
     rall
    0.06
     shared
    0.06
     User
    0.06
    Activations Density 0.081%

    No Known Activations