© 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. 129772
    Prev
    Next
    INDEX
    Explanations

    taxes, duties, tariffs, charges, rise, rates

    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
     prototype
    -0.06
    illumin
    -0.06
    initial
    -0.06
     Initial
    -0.06
     रोजाना
    -0.06
     bomber
    -0.06
     आएगा
    -0.06
     indicative
    -0.06
     ballot
    -0.06
     holotype
    -0.06
    POSITIVE LOGITS
     semua
    0.07
     capacidades
    0.06
    для
    0.06
     slope
    0.06
     Несмотря
    0.06
     unchanged
    0.06
     wszyscy
    0.06
     slopes
    0.06
     všetky
    0.06
     toate
    0.06
    Activations Density 0.025%

    No Known Activations