© 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. 86922
    Prev
    Next
    INDEX
    Explanations

    academic programs and courses

    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
    куртка
    -0.86
     مخصوص
    -0.79
     tuần
    -0.78
    ifts
    -0.77
    ציה
    -0.75
    футболка
    -0.75
    chmal
    -0.74
    ⼆
    -0.74
     foothills
    -0.74
    posium
    -0.73
    POSITIVE LOGITS
     programs
    2.70
     programmes
    2.31
     program
    2.30
     programas
    2.03
    Programs
    2.00
    programs
    1.95
     Programs
    1.91
    program
    1.85
     programme
    1.73
     courses
    1.69
    Activations Density 0.044%

    No Known Activations