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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110470
    Prev
    Next
    INDEX
    Explanations

    DISPLAYTITLE or display:

    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
     uğ
    -0.76
     AER
    -0.76
    ーツ
    -0.74
    就已经
    -0.71
    おわりに
    -0.71
    Ⅳ
    -0.69
    eland
    -0.69
    Nad
    -0.68
     memegang
    -0.68
    Коммента
    -0.67
    POSITIVE LOGITS
     Display
    1.27
     display
    1.20
    Display
    1.18
     DISPLAY
    1.12
     inline
    1.06
    display
    1.03
     displaying
    1.03
     block
    1.03
     displayed
    0.94
    displayed
    0.93
    Activations Density 0.003%

    No Known Activations