© 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. 40-GEMMASCOPE-2-RES-262K
    7. 85169
    Prev
    Next
    INDEX
    Explanations

    X-time achievements

    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_40_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
    循环
    0.41
    琭
    0.40
     categories
    0.40
     duplication
    0.39
    ēng
    0.39
    czech
    0.39
    emples
    0.39
    uire
    0.39
     competition
    0.37
     duplicating
    0.37
    POSITIVE LOGITS
     All
    0.63
    All
    0.57
     twice
    0.53
    選
    0.52
     zweimal
    0.52
     First
    0.49
     Все
    0.47
     オール
    0.47
     ऑल
    0.47
    twice
    0.46
    Activations Density 0.004%

    No Known Activations