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. 7869
    Prev
    Next
    INDEX
    Explanations

    words starting with Ly

    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
    ⲁ
    -0.86
    超過
    -0.82
     provoking
    -0.79
     circumstances
    -0.77
    paymentMethod
    -0.75
     particolari
    -0.75
     Acqua
    -0.74
    𝙩
    -0.73
    oxia
    -0.73
     descends
    -0.73
    POSITIVE LOGITS
     Ly
    1.57
     ly
    1.45
    Ly
    1.41
     LY
    1.17
     Lyon
    1.00
     Lyman
    0.98
     Lyons
    0.90
     Lynda
    0.88
     Lyt
    0.86
    lyk
    0.83
    Activations Density 0.034%

    No Known Activations