© 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. 117223
    Prev
    Next
    INDEX
    Explanations

    or, or, or

    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
    These
    -0.06
     fundraising
    -0.06
     would
    -0.06
     raising
    -0.06
     allows
    -0.06
     government
    -0.06
     There
    -0.06
     ticketing
    -0.06
     rainbow
    -0.06
     governments
    -0.06
    POSITIVE LOGITS
    または
    0.07
     oder
    0.07
     vagy
    0.07
     meist
    0.07
     அல்லது
    0.07
     manchmal
    0.07
     responsable
    0.06
     లేదా
    0.06
     또는
    0.06
     talvez
    0.06
    Activations Density 0.002%

    No Known Activations