© 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. 118818
    Prev
    Next
    INDEX
    Explanations

    youtube.com/watch?

    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
    Lib
    -0.80
    霑
    -0.77
     sui
    -0.76
    Reading
    -0.74
     Slack
    -0.74
    readers
    -0.73
     specifik
    -0.73
    ≈
    -0.73
    britannien
    -0.73
     digitale
    -0.72
    POSITIVE LOGITS
     watch
    2.84
    watch
    2.73
     Watch
    2.19
     WATCH
    1.99
    Watch
    1.93
    WATCH
    1.78
     watched
    1.65
     watches
    1.62
     watchdog
    1.20
    watches
    1.17
    Activations Density 0.005%

    No Known Activations