© 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. 34-GEMMASCOPE-RES-131K
    7. 110701
    Prev
    Next
    INDEX
    Explanations

    `loginUser` or code keywords

    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
    创建一个
    -0.88
     Kebijakan
    -0.87
     Karten
    -0.84
    Já
    -0.84
    总数
    -0.84
    getSelectedItem
    -0.78
     chanson
    -0.77
    したもの
    -0.77
     vídeo
    -0.76
    خوا
    -0.75
    POSITIVE LOGITS
    loginUser
    1.04
     loginUser
    0.91
     papild
    0.88
    ]*
    0.88
     actionTypes
    0.85
    凄い
    0.83
    …」
    0.82
    ">{{$
    0.82
     einzel
    0.81
    irmingham
    0.80
    Activations Density 0.034%

    No Known Activations