© 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. 118819
    Prev
    Next
    INDEX
    Explanations

    frequency, Fourier, transforms

    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
    aunque
    -0.07
     deficiencies
    -0.06
    uest
    -0.06
     aunque
    -0.06
     یون
    -0.06
     fiatal
    -0.06
    苃
    -0.06
    Would
    -0.05
    insol
    -0.05
     விரு
    -0.05
    POSITIVE LOGITS
     certainty
    0.07
     echt
    0.06
     zeker
    0.06
     مرح
    0.06
     zatim
    0.06
     LA
    0.06
     placa
    0.06
     THE
    0.06
    secure
    0.05
     more
    0.05
    Activations Density 0.003%

    No Known Activations