© 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. 27823
    Prev
    Next
    INDEX
    Explanations

    tokenization and word breakdown

    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
     পাকসেন
    0.46
     出
    0.41
     تصميم
    0.41
    াসী
    0.40
    出版社
    0.39
     história
    0.39
    ించాడు
    0.39
    نگ
    0.39
    Roberts
    0.39
    יוחד
    0.39
    POSITIVE LOGITS
    я
    0.49
    难以
    0.47
     трудно
    0.44
     сельскохозяй
    0.44
    Khal
    0.40
     Yoruba
    0.40
    бу
    0.40
    जैसा
    0.40
    по
    0.40
    さまざまな
    0.39
    Activations Density 0.004%

    No Known Activations