© 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. 119145
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
     basically
    -0.06
    と考えて
    -0.06
     homeostasis
    -0.06
    と思って
    -0.06
     underserved
    -0.06
     altos
    -0.06
     থাকলেও
    -0.06
     Globalization
    -0.06
           
    -0.06
    POSITIVE LOGITS
    에서는
    0.06
     修改
    0.06
    unlike
    0.06
     supernatant
    0.06
     отличи
    0.06
     अथवा
    0.06
     diminutive
    0.06
    哪些
    0.05
     vice
    0.05
    vice
    0.05
    Activations Density 0.044%

    No Known Activations