© 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. 36360
    Prev
    Next
    INDEX
    Explanations

    assignment and declaration symbols

    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
    Ț
    -1.27
    Ħ
    -1.25
    ЖИ
    -1.22
    ฿
    -1.20
    РТ
    -1.20
     bicicleta
    -1.18
     garçon
    -1.16
     brancas
    -1.14
    ʺ
    -1.13
     Lexikon
    -1.11
    POSITIVE LOGITS
     dieselben
    1.35
    除此
    1.15
    意思是
    1.14
    额外
    1.13
     derselben
    1.09
    结语
    1.08
     dasselbe
    1.06
     テーブル
    1.05
    Medida
    1.05
     inmediato
    1.04
    Activations Density 0.015%

    No Known Activations