© 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. 22-GEMMASCOPE-RES-131K
    7. 39661
    Prev
    Next
    INDEX
    Explanations

    complete or total state

    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_22/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
     dando
    -3.13
    ↵↵
    -2.92
     stalwart
    -2.88
     pivotal
    -2.75
     decidedly
    -2.67
    -2.56
     crucial
    -2.56
     пять
    -2.48
    .
    -2.47
    often
    -2.45
    POSITIVE LOGITS
    棪
    2.80
     शुर
    2.78
     categorized
    2.77
    although
    2.75
     Some
    2.73
     Although
    2.70
     However
    2.70
    鯪
    2.69
     Even
    2.66
    祧
    2.64
    Activations Density 0.018%

    No Known Activations