© 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. 102511
    Prev
    Next
    INDEX
    Explanations

    text editors and IDEs

    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
    rindo
    -0.78
     multicast
    -0.71
    peras
    -0.71
    witzerland
    -0.70
     puramente
    -0.69
     jurid
    -0.68
    élien
    -0.67
     imperme
    -0.66
     diaphrag
    -0.65
    embols
    -0.65
    POSITIVE LOGITS
     editor
    4.81
    editor
    4.13
     Editor
    3.95
     editors
    3.78
    Editor
    3.67
     EDITOR
    3.13
     IDE
    3.05
    EDITOR
    2.92
     Editors
    2.91
    editors
    2.83
    Activations Density 0.180%

    No Known Activations