© 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. 120356
    Prev
    Next
    INDEX
    Explanations

    en-dash or em-dash separators

    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
    dd
    -0.06
     sementara
    -0.06
    Queensland
    -0.06
     where
    -0.06
     เหมาะ
    -0.06
     กับ
    -0.06
     lucky
    -0.05
    6
    -0.05
     постара
    -0.05
     حيث
    -0.05
    POSITIVE LOGITS
    Lose
    0.06
     give
    0.06
     otorg
    0.06
    Nowadays
    0.06
     समक्ष
    0.06
     called
    0.06
     January
    0.06
     decrease
    0.06
     nende
    0.06
     meines
    0.06
    Activations Density 0.003%

    No Known Activations