© 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. 11006
    Prev
    Next
    INDEX
    Explanations

    learning and reading

    np_acts-logits-general · gemini-2.5-flash-lite

    learning resources

    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
     roofs
    0.52
    LEY
    0.51
    金具
    0.50
    স
    0.47
    arranty
    0.47
    房屋
    0.47
    restaurants
    0.46
    ୋ
    0.46
    ಾಯ
    0.46
     frontage
    0.46
    POSITIVE LOGITS
     공부해
    1.11
     изучение
    1.05
    学习
    1.00
    的学习
    1.00
     공부
    1.00
     مطالعه
    0.99
    阅读
    0.98
     studying
    0.98
     aprendizaje
    0.97
     Studying
    0.96
    Activations Density 0.221%

    No Known Activations