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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8283
    Prev
    Next
    INDEX
    Explanations

    case, skip, now, .com, "

    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
     OnClickListener
    -0.85
    alisis
    -0.82
    erker
    -0.81
    홈
    -0.79
    書き
    -0.77
     glorious
    -0.76
     Deportes
    -0.76
    र्
    -0.75
    entiary
    -0.74
     детских
    -0.72
    POSITIVE LOGITS
     unknown
    0.85
     OX
    0.81
     Wire
    0.79
    wholesome
    0.78
    huahua
    0.77
     térm
    0.77
    %*
    0.76
    DateRange
    0.75
     здоров
    0.75
    WinForms
    0.74
    Activations Density 0.001%

    No Known Activations