© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130020
    Prev
    Next
    INDEX
    Explanations

    callback related 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
     available
    -0.07
    就要
    -0.06
    available
    -0.06
     zunächst
    -0.06
     دستیاب
    -0.06
    ինչ
    -0.06
    Available
    -0.06
     чтобы
    -0.06
    credit
    -0.06
     disponibili
    -0.06
    POSITIVE LOGITS
     are
    0.07
     other
    0.06
     আমার
    0.06
     لا
    0.06
     감사합니다
    0.06
     な
    0.06
    avaient
    0.06
     mijn
    0.06
     profond
    0.06
    scaron
    0.06
    Activations Density 0.003%

    No Known Activations