© 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. 129405
    Prev
    Next
    INDEX
    Explanations

    questions, what, trade

    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
    自由
    -0.07
     comedies
    -0.07
     자유
    -0.06
    而非
    -0.06
     ambul
    -0.06
    вые
    -0.06
     Geschichten
    -0.06
     glycoproteins
    -0.06
    Freedom
    -0.06
     barrel
    -0.06
    POSITIVE LOGITS
    бий
    0.06
     எங்க
    0.06
     procedimento
    0.05
    彼此
    0.05
    Song
    0.05
     birbir
    0.05
    ขั้นตอน
    0.05
     സഹ
    0.05
     colliding
    0.05
    kA
    0.05
    Activations Density 0.007%

    No Known Activations