© 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. 118132
    Prev
    Next
    INDEX
    Explanations

    file path components and prefixes

    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
     với
    -0.08
     with
    -0.07
     الجميع
    -0.06
    年月
    -0.06
     जिसमे
    -0.06
     ชื่อ
    -0.06
     होण्याची
    -0.06
     to
    -0.06
    ชื่อ
    -0.06
     सेमी
    -0.05
    POSITIVE LOGITS
     دائما
    0.07
    :
    0.07
     systematically
    0.06
    一定要
    0.06
    !“
    0.06
    !`
    0.06
     selalu
    0.06
     systematic
    0.06
     Siempre
    0.06
     always
    0.06
    Activations Density 0.002%

    No Known Activations