© 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. 10-GEMMASCOPE-RES-131K
    7. 21946
    Prev
    Next
    INDEX
    Explanations

    is a kind of behavior

    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_10/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
    Ꭳ
    -3.36
    檍
    -3.03
    ..?
    -2.83
    橚
    -2.75
     ?.
    -2.73
    槩
    -2.70
     geel
    -2.69
     blauw
    -2.66
    
    -2.63
    ;-
    -2.59
    POSITIVE LOGITS
     keď
    2.78
     We
    2.77
    ſelves
    2.52
     や
    2.48
     If
    2.41
    y
    2.39
     selben
    2.39
     Because
    2.33
     länge
    2.33
    不忘
    2.28
    Activations Density 0.001%

    No Known Activations