© 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. 117948
    Prev
    Next
    INDEX
    Explanations

    assignment or equality

    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
    yorum
    -0.08
     photographs
    -0.07
     toate
    -0.07
    PERATURE
    -0.06
    用于
    -0.06
     इच्छ
    -0.06
    always
    -0.06
     selalu
    -0.06
    рован
    -0.06
     simplest
    -0.06
    POSITIVE LOGITS
     있는데요
    0.06
     of
    0.06
     leakage
    0.06
     लाइफ
    0.06
     &
    0.06
     Iconic
    0.06
     వై
    0.06
    ‎
    0.06
     characteristic
    0.05
     River
    0.05
    Activations Density 0.002%

    No Known Activations