© 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. 90774
    Prev
    Next
    INDEX
    Explanations

    making an appearance

    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
    лены
    -0.73
    CTS
    -0.73
    prefix
    -0.72
     чемпи
    -0.71
     Doodle
    -0.68
    omeric
    -0.68
     الدن
    -0.68
     детства
    -0.68
     حجم
    -0.68
    ATHERINE
    -0.68
    POSITIVE LOGITS
     appearance
    4.69
     appearances
    4.00
    appearance
    3.36
     Appearance
    3.14
    Appearance
    3.02
     appeared
    2.55
     Appearances
    2.53
     appear
    2.50
    Appearances
    2.48
     appea
    2.31
    Activations Density 0.059%

    No Known Activations