© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128788
    Prev
    Next
    INDEX
    Explanations

    #define and const keywords

    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
    *,
    -0.06
     ഇത്തരം
    -0.06
     Thursday
    -0.06
     menawarkan
    -0.06
    ;,
    -0.06
    !,
    -0.06
    processing
    -0.06
     encouraging
    -0.06
    这种
    -0.06
     टीमें
    -0.05
    POSITIVE LOGITS
     heist
    0.06
     पर्या
    0.06
     primarily
    0.06
    了嗎
    0.06
    そこに
    0.06
     its
    0.06
     பெய
    0.06
     entrenamiento
    0.06
     treino
    0.06
    ሥ
    0.06
    Activations Density 0.004%

    No Known Activations