© 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. 22-GEMMASCOPE-RES-131K
    7. 12392
    Prev
    Next
    INDEX
    Explanations

    great new ideas

    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
    奬
    -1.64
    部份
    -1.41
     назва
    -1.41
     hitherto
    -1.34
     heretofore
    -1.33
     utterly
    -1.33
     superbly
    -1.33
     unrelenting
    -1.30
    修为
    -1.30
     supremely
    -1.28
    POSITIVE LOGITS
     COVID
    1.72
     covid
    1.58
     pesso
    1.49
     TikTok
    1.49
     verschillende
    1.45
     также
    1.45
     ľudí
    1.44
    ౮
    1.43
     également
    1.41
     "[
    1.41
    Activations Density 0.004%

    No Known Activations