© 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. 82899
    Prev
    Next
    INDEX
    Explanations

    line and bar charts

    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
    fontawesome
    -0.75
     getById
    -0.72
     计算
    -0.72
    gulama
    -0.70
    тесь
    -0.69
    äuser
    -0.69
     unlucky
    -0.68
     Cuts
    -0.67
     wiecz
    -0.67
     RecyclerView
    -0.67
    POSITIVE LOGITS
     line
    2.45
     Line
    2.16
    Line
    2.11
    line
    2.08
    LINE
    1.78
     bar
    1.74
    getLine
    1.72
     LINE
    1.65
     Bar
    1.63
     charts
    1.59
    Activations Density 0.070%

    No Known Activations