© 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. 129252
    Prev
    Next
    INDEX
    Explanations

    countries and people

    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
     برای
    -0.07
    .
    -0.07
     journalist
    -0.06
     congratulations
    -0.06
    ras
    -0.06
    thanks
    -0.06
     για
    -0.06
     backdrop
    -0.06
     policeman
    -0.06
    ات
    -0.06
    POSITIVE LOGITS
     whispering
    0.06
    ujący
    0.06
     முழு
    0.06
    気になる
    0.06
     உன்
    0.06
    不但
    0.06
     olyan
    0.06
     subtly
    0.06
    以後
    0.06
     vragen
    0.05
    Activations Density 0.001%

    No Known Activations