© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60562
    Prev
    Next
    INDEX
    Explanations

    using statements and namespaces

    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_34/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
    ならでは
    -0.90
     integra
    -0.90
     them
    -0.83
    皆さん
    -0.83
     gusta
    -0.83
    ブログ村
    -0.82
    みなさん
    -0.80
    皆様
    -0.79
    みなさま
    -0.78
    ナメント
    -0.78
    POSITIVE LOGITS
    EDEFAULT
    1.02
    抡
    0.86
    namics
    0.85
     DataBase
    0.83
    FORMS
    0.79
    鈞
    0.78
     ".";
    0.77
     ɛ
    0.77
    DETECT
    0.77
    ниці
    0.76
    Activations Density 0.006%

    No Known Activations