© 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. 119522
    Prev
    Next
    INDEX
    Explanations

    Shana, mysterious, stepwise

    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
     나오고
    -0.07
     peac
    -0.06
     oppressed
    -0.06
    最後
    -0.06
     unnatural
    -0.06
     unhealthy
    -0.06
     उभर
    -0.06
     VIDE
    -0.06
     manière
    -0.06
     الکتر
    -0.06
    POSITIVE LOGITS
     jewelry
    0.06
     zejména
    0.06
     moglie
    0.06
     Mueller
    0.06
     exothermic
    0.06
     toughest
    0.06
     bestselling
    0.06
     especially
    0.06
    😘
    0.06
    <th>
    0.06
    Activations Density 0.003%

    No Known Activations