© 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. 129990
    Prev
    Next
    INDEX
    Explanations

    although, herein, matter, believe, well, common, mostly

    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
    мати
    -0.06
     pursuing
    -0.06
     দেহ
    -0.06
     then
    -0.06
     rồi
    -0.06
     garis
    -0.06
    unun
    -0.06
    佢
    -0.06
     ভয়ঙ্কর
    -0.06
     prowad
    -0.05
    POSITIVE LOGITS
    ~!
    0.06
     بالإضافة
    0.06
     nonché
    0.06
    ..!
    0.06
    ...!
    0.06
     están
    0.06
     on
    0.06
     diferente
    0.06
     entreprise
    0.06
     më
    0.06
    Activations Density 0.006%

    No Known Activations