© 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. 128450
    Prev
    Next
    INDEX
    Explanations

    code or numbers following parentheses

    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
    стный
    -0.07
    など
    -0.07
     sehr
    -0.06
    まさに
    -0.06
     в
    -0.06
    дный
    -0.06
     వెంటనే
    -0.06
    を
    -0.06
     등
    -0.06
     as
    -0.06
    POSITIVE LOGITS
     receiving
    0.07
     being
    0.06
     percentage
    0.06
     getting
    0.06
     commenced
    0.06
     attaching
    0.06
     beginning
    0.06
     having
    0.06
     punishable
    0.06
     coming
    0.06
    Activations Density 0.003%

    No Known Activations