© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84219
    Prev
    Next
    INDEX
    Explanations

    places and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.99
    刑事
    -0.99
    鴉
    -0.97
    ẢN
    -0.96
    MeasureSpec
    -0.96
    講師
    -0.94
     cetera
    -0.94
    [])
    -0.94
    👊
    -0.94
    -0.93
    POSITIVE LOGITS
     noastre
    1.28
    凄く
    1.18
    あー
    1.16
    あんな
    1.13
    割と
    1.10
    めちゃくちゃ
    1.09
    未だ
    1.08
    えっ
    1.06
    どれだけ
    1.05
     alltid
    1.04
    Activations Density 0.002%

    No Known Activations