© 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. 10-GEMMASCOPE-RES-131K
    7. 504
    Prev
    Next
    INDEX
    Explanations

    questions, code, dates, and recent 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_10/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
    采用了
    -2.80
    ᠁
    -2.77
     snart
    -2.75
     hennes
    -2.72
    ኧ
    -2.67
    儈
    -2.64
     kommet
    -2.63
     всѣ
    -2.63
    ൎ
    -2.61
    
    -2.61
    POSITIVE LOGITS
     of
    2.89
    ↵↵
    2.80
     zwłaszcza
    2.61
    </u>
    2.55
    <b>
    2.50
     duże
    2.42
     protože
    2.38
    C
    2.36
     In
    2.36
    ↵
    2.36
    Activations Density 0.001%

    No Known Activations