© 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. 73753
    Prev
    Next
    INDEX
    Explanations

    delete, update, insert

    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
     modification
    -1.83
     modify
    -1.75
    modify
    -1.73
    修改
    -1.72
     modified
    -1.72
     modifications
    -1.68
    MODIFY
    -1.64
     edit
    -1.60
    Modify
    -1.59
     modifying
    -1.59
    POSITIVE LOGITS
     delete
    0.81
     deletes
    0.81
    蒻
    0.74
    dirkan
    0.72
     Delete
    0.71
     consens
    0.71
     ਕ
    0.71
     Kalk
    0.70
     voyages
    0.70
     Rine
    0.69
    Activations Density 0.038%

    No Known Activations