© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 241883
    Prev
    Next
    INDEX
    Explanations

    Christmas, questions, from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trois
    0.50
     Конститу
    0.50
     Dragon
    0.49
     Nhiều
    0.49
    潾
    0.49
     Village
    0.49
     บาง
    0.49
     Spinner
    0.49
     Ростов
    0.48
     Cách
    0.48
    POSITIVE LOGITS
     angiel
    0.55
     contextos
    0.50
     kontek
    0.49
    ença
    0.47
     évén
    0.46
     anglais
    0.46
    ات
    0.45
     angry
    0.44
    다
    0.44
    ى
    0.44
    Activations Density 0.001%

    No Known Activations