© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14007
    Prev
    Next
    INDEX
    Explanations

    foreign or specific scripts

    np_acts-logits-general · gemini-2.5-flash-lite

    list diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    מי
    0.54
    נ
    0.54
     suelos
    0.52
    연
    0.52
    יו
    0.52
    מו
    0.50
    嘏
    0.50
    ุล
    0.49
    넣
    0.48
    נו
    0.47
    POSITIVE LOGITS
    unday
    0.47
    なのですが
    0.46
    还可以
    0.46
     savoury
    0.46
    楽しめる
    0.45
     വിവിധ
    0.44
     मसाले
    0.44
    可以使用
    0.44
     Tất
    0.44
    ädchen
    0.43
    Activations Density 0.003%

    No Known Activations