© 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. 128354
    Prev
    Next
    INDEX
    Explanations

    usernames or names

    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
     of
    -0.08
     Bowers
    -0.06
     dó
    -0.06
    adat
    -0.06
    当年
    -0.06
     at
    -0.06
     even
    -0.06
    лю
    -0.06
    kre
    -0.05
    重大
    -0.05
    POSITIVE LOGITS
    Ｖ
    0.07
    DELAY
    0.06
     розташо
    0.06
     появились
    0.06
     गायब
    0.06
     toutes
    0.06
    虜
    0.06
     znal
    0.06
     periodicals
    0.06
    이라면
    0.06
    Activations Density 0.008%

    No Known Activations