© 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-65K
    7. 1163
    Prev
    Next
    INDEX
    Explanations

    collections namespace and types

    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_65k_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
    ාවිත
    0.42
    嘈
    0.42
    urlopen
    0.41
    ោ
    0.39
     synthase
    0.39
    Фе
    0.39
    癤
    0.39
    kprop
    0.38
    __[
    0.38
    퐫
    0.37
    POSITIVE LOGITS
    Collections
    0.71
     Special
    0.66
     Collections
    0.65
    Special
    0.62
    special
    0.60
    IEnumerable
    0.58
     special
    0.57
     collections
    0.56
     Concurrent
    0.53
    ObjectModel
    0.53
    Activations Density 0.006%

    No Known Activations