© 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. 128345
    Prev
    Next
    INDEX
    Explanations

    code output delimiters

    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
     each
    -0.07
    虽然
    -0.07
    salir
    -0.07
    还是很
    -0.07
    each
    -0.07
     каждый
    -0.07
     každý
    -0.06
     según
    -0.06
    每个
    -0.06
     mentre
    -0.06
    POSITIVE LOGITS
     over
    0.08
     in
    0.08
     from
    0.07
     after
    0.06
     within
    0.06
     across
    0.06
     utilizing
    0.06
     utilizando
    0.06
     Print
    0.06
     outcrops
    0.06
    Activations Density 0.003%

    No Known Activations