© 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. 120260
    Prev
    Next
    INDEX
    Explanations

    acting career, television series, and films

    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
    뭐
    -0.07
     뭐
    -0.06
     बदलते
    -0.06
    Après
    -0.06
     marrón
    -0.06
     novo
    -0.06
     Godfather
    -0.06
    Despite
    -0.06
     instead
    -0.06
     godfather
    -0.06
    POSITIVE LOGITS
    navigationItem
    0.07
     ಹಾಗೂ
    0.06
    лили
    0.06
    TWO
    0.06
     இரண்டு
    0.06
    શ્ર
    0.05
     deux
    0.05
     lets
    0.05
     TWO
    0.05
     宮
    0.05
    Activations Density 0.011%

    No Known Activations