© 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. 4121
    Prev
    Next
    INDEX
    Explanations

    interactive discussion forum

    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
     courses
    -0.90
     catalog
    -0.82
     schools
    -0.79
     ユーザー
    -0.76
     school
    -0.73
     schooling
    -0.73
     Catalog
    -0.71
    课堂
    -0.71
     classroom
    -0.69
     ensino
    -0.69
    POSITIVE LOGITS
     Discussion
    1.08
    Discussion
    0.98
     activity
    0.97
     Kegiatan
    0.96
     Discussions
    0.94
     discussion
    0.93
     forum
    0.92
     attività
    0.90
    discussion
    0.88
     actividad
    0.86
    Activations Density 0.022%

    No Known Activations