© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72034
    Prev
    Next
    INDEX
    Explanations

    logging messages and events

    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
     货
    -0.95
    dhan
    -0.95
     choices
    -0.94
     Ảnh
    -0.88
     امید
    -0.88
     音乐
    -0.88
    性命
    -0.88
    れている
    -0.88
     chré
    -0.87
     客户
    -0.86
    POSITIVE LOGITS
     record
    1.02
    createTextNode
    0.98
    Record
    0.96
     documenting
    0.96
     escrit
    0.95
    记录
    0.94
     Entstehung
    0.93
    Encontra
    0.92
     later
    0.92
    WidgetItem
    0.92
    Activations Density 0.008%

    No Known Activations