© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100025
    Prev
    Next
    INDEX
    Explanations

    We'll, to, between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hill
    0.39
     Scal
    0.39
     einzelne
    0.39
    数
    0.38
     Mascot
    0.38
    Moore
    0.38
    м
    0.38
     Mt
    0.37
     Community
    0.37
     Moore
    0.37
    POSITIVE LOGITS
    成绩
    0.49
     ထ
    0.48
    ıdır
    0.48
    اکي
    0.48
     is
    0.47
     הייתה
    0.47
     warmly
    0.47
    启用
    0.46
    原生
    0.46
     کامیابی
    0.46
    Activations Density 0.003%

    No Known Activations