© 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. 117508
    Prev
    Next
    INDEX
    Explanations

    email structure

    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
     convo
    -0.07
    aissez
    -0.06
     registrados
    -0.06
     engineering
    -0.06
     modelling
    -0.06
     công
    -0.06
     Modelling
    -0.06
     publicly
    -0.06
     ศ
    -0.06
     goods
    -0.06
    POSITIVE LOGITS
     ಕೆಲಸ
    0.06
     Gda
    0.06
     morning
    0.06
     ईसाई
    0.06
     Postgres
    0.06
     brunch
    0.06
     каждое
    0.06
    kee
    0.06
     Jolla
    0.06
     Samba
    0.06
    Activations Density 0.005%

    No Known Activations