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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7921
    Prev
    Next
    INDEX
    Explanations

    wife, brides, or orders

    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
    utus
    -0.74
     obdob
    -0.74
    親子
    -0.72
     Champlain
    -0.71
     eğiti
    -0.69
     uží
    -0.68
    簍
    -0.67
    諸
    -0.67
    nsylvania
    -0.66
     dianteira
    -0.66
    POSITIVE LOGITS
     bride
    2.98
     brides
    2.67
     Bride
    2.23
     wife
    2.09
    bride
    1.97
    Bride
    1.95
     Brides
    1.76
     wives
    1.73
     mail
    1.69
    brides
    1.58
    Activations Density 0.021%

    No Known Activations