© 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. 50242
    Prev
    Next
    INDEX
    Explanations

    Todd Wilson

    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
    imedia
    -0.74
    iala
    -0.74
     Ora
    -0.72
    rejo
    -0.70
    cially
    -0.70
    接收
    -0.69
     NSMutable
    -0.69
     Successful
    -0.68
     Royale
    -0.68
     EASY
    -0.68
    POSITIVE LOGITS
     views
    0.94
     range
    0.87
     view
    0.86
     ranges
    0.85
    ENSOR
    0.84
    View
    0.81
     evalu
    0.78
     قسمت
    0.78
     vial
    0.77
     Views
    0.76
    Activations Density 0.027%

    No Known Activations