© 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. 119100
    Prev
    Next
    INDEX
    Explanations

    `name`, `datetime`, `String`, `int` definitions

    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
    anız
    -0.06
     semana
    -0.06
     meinem
    -0.06
     Minggu
    -0.06
     yönt
    -0.06
     configurações
    -0.06
     vaporizer
    -0.06
     presentaciones
    -0.06
     ۴
    -0.06
     हाम्रो
    -0.06
    POSITIVE LOGITS
     of
    0.08
     for
    0.08
    利用
    0.07
     cf
    0.06
    随着
    0.06
     called
    0.06
     from
    0.06
     বিল
    0.06
     ratione
    0.06
     се
    0.06
    Activations Density 0.003%

    No Known Activations