© 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. 93355
    Prev
    Next
    INDEX
    Explanations

    punctuation and list conjunctions

    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
    นะนำ
    -1.09
     syk
    -0.92
     hata
    -0.90
    Более
    -0.90
    un
    -0.89
    vého
    -0.88
    量的
    -0.86
    p
    -0.86
     jaj
    -0.86
     Universite
    -0.85
    POSITIVE LOGITS
    に似
    1.34
     
    1.34
     álcool
    1.30
    だらけ
    1.29
    が良い
    1.28
    ごめんなさい
    1.27
    シルバー
    1.27
    ほら
    1.26
    によく
    1.25
     nasz
    1.23
    Activations Density 0.054%

    No Known Activations