© 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. 116297
    Prev
    Next
    INDEX
    Explanations

    retail or commercial entities

    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
     آل
    -0.06
     воздействия
    -0.06
    里
    -0.05
    erate
    -0.05
     Countries
    -0.05
     achat
    -0.05
     dazz
    -0.05
     purchased
    -0.05
     Thủ
    -0.05
     देश
    -0.05
    POSITIVE LOGITS
     will
    0.08
     Interests
    0.07
     premium
    0.06
     interés
    0.06
     represented
    0.06
     interests
    0.06
     new
    0.06
     interest
    0.06
     ссы
    0.06
    will
    0.06
    Activations Density 0.012%

    No Known Activations