© 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. 107407
    Prev
    Next
    INDEX
    Explanations

    display, style, jeans

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

    using or requiring certain context

    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
     ক্ষতিগ্রস্ত
    0.51
    音乐
    0.49
    服务
    0.48
    🏍
    0.46
     নৃত্য
    0.46
     প্রয়োজনে
    0.45
    Hoje
    0.45
    🌻
    0.45
     появится
    0.44
    资源
    0.43
    POSITIVE LOGITS
     esprit
    0.59
     dyspe
    0.57
     unquestion
    0.54
     doctrinal
    0.52
     zeal
    0.50
     niacin
    0.50
     moral
    0.50
     undue
    0.49
     diarrh
    0.49
     metap
    0.49
    Activations Density 0.000%

    No Known Activations