© 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. 117777
    Prev
    Next
    INDEX
    Explanations

    usernames ending in names

    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
     عندي
    -0.07
     অসুবিধা
    -0.07
    情報
    -0.06
     relations
    -0.06
     내용
    -0.06
     చెప్ప
    -0.06
     Extensive
    -0.06
     আমার
    -0.06
    Vancouver
    -0.06
    Comprehensive
    -0.06
    POSITIVE LOGITS
     in
    0.07
     निः
    0.06
     эн
    0.06
     (*)
    0.05
     varying
    0.05
     നിറഞ്ഞ
    0.05
    就连
    0.05
     (=
    0.05
     alcanzó
    0.05
     shutter
    0.05
    Activations Density 0.006%

    No Known Activations