© 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. 118277
    Prev
    Next
    INDEX
    Explanations

    code block markers and 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
     rehabilitation
    -0.06
     ഇതി
    -0.06
     an
    -0.06
     its
    -0.06
     листо
    -0.05
     അതിന്റെ
    -0.05
    AD
    -0.05
    searching
    -0.05
    Makefile
    -0.05
    tale
    -0.05
    POSITIVE LOGITS
     Example
    0.08
     zuvor
    0.06
     EXAMPLE
    0.06
     предыду
    0.06
     바뀌
    0.06
     Vậy
    0.06
     преж
    0.06
    仍
    0.06
    仍然
    0.06
     前回
    0.06
    Activations Density 0.004%

    No Known Activations