© 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. 107610
    Prev
    Next
    INDEX
    Explanations

    editor's note

    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
    老爷
    -0.69
     berikan
    -0.69
    onSelect
    -0.68
    clone
    -0.68
     outlines
    -0.68
     مفص
    -0.68
    tudi
    -0.66
     packaged
    -0.66
     Finally
    -0.65
    Externí
    -0.65
    POSITIVE LOGITS
    Editor
    3.72
     Editor
    3.61
     editor
    3.44
    editor
    3.14
    EDITOR
    2.97
     Editors
    2.86
    Editors
    2.81
     editors
    2.80
     note
    2.70
     EDITOR
    2.66
    Activations Density 0.037%

    No Known Activations