© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131050
    Prev
    Next
    INDEX
    Explanations

    Red Wings

    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
     the
    -0.06
    :
    -0.06
     What
    -0.06
     `
    -0.06
     با
    -0.05
     comme
    -0.05
     no
    -0.05
    数字
    -0.05
     with
    -0.05
    ely
    -0.05
    POSITIVE LOGITS
     способствует
    0.07
     afectan
    0.07
     поддержка
    0.06
    ódio
    0.06
    見
    0.06
    出会
    0.06
     نشر
    0.06
     komponen
    0.06
    NESS
    0.06
     determinato
    0.06
    Activations Density 0.014%

    No Known Activations