© 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. 129627
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
     thousands
    -0.06
    ͅ
    -0.05
     ứng
    -0.05
     ഒന്നും
    -0.05
     his
    -0.05
     רי
    -0.05
    وره
    -0.05
     perfecta
    -0.05
     giusta
    -0.05
     millions
    -0.05
    POSITIVE LOGITS
     baroque
    0.07
     incorporates
    0.06
     reflects
    0.06
     aeg
    0.06
    responsible
    0.06
     describes
    0.06
     cristall
    0.06
     exemplifies
    0.06
     чрез
    0.06
     has
    0.06
    Activations Density 0.002%

    No Known Activations