© 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. 129380
    Prev
    Next
    INDEX
    Explanations

    buy tickets or eat grapes

    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
     〢
    -0.06
     matcha
    -0.06
     companions
    -0.06
    makeup
    -0.06
     newsletter
    -0.06
     raind
    -0.05
    出席
    -0.05
     raspberries
    -0.05
     Ganges
    -0.05
     manicure
    -0.05
    POSITIVE LOGITS
    various
    0.06
     вмеша
    0.06
     möglicherweise
    0.06
     пыта
    0.06
     मिश्र
    0.06
     vytvá
    0.06
     चैंपियन
    0.06
     exclusivement
    0.06
     평가
    0.06
    上述
    0.06
    Activations Density 0.008%

    No Known Activations