Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by activity

    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
     -
    -2.55
     for
    -1.94
     is
    -1.79
    悪く
    -1.74
     così
    -1.73
    X
    -1.73
    
    -1.71
     комнаты
    -1.70
    其他人
    -1.63
     always
    -1.58
    POSITIVE LOGITS
     手作り
    2.08
     montrant
    1.90
    icii
    1.85
    fatta
    1.82
    我覺得
    1.81
     水彩
    1.79
    轳
    1.79
     économies
    1.77
    )});
    1.76
    ~•
    1.76
    Activations Density 0.012%

    No Known Activations