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. 7952
    Prev
    Next
    INDEX
    Explanations

    academic and technical titles

    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
    ratos
    -0.75
    definition
    -0.73
    消息
    -0.72
    dotte
    -0.72
     Synchronous
    -0.69
    锂
    -0.69
    Domain
    -0.68
    synchron
    -0.67
    اوى
    -0.67
     '.'
    -0.66
    POSITIVE LOGITS
     cca
    0.79
    ContentType
    0.77
    קט
    0.77
    árny
    0.77
     تاپ
    0.77
     müm
    0.76
    PageContext
    0.74
     ප
    0.71
    ТЫ
    0.70
    ział
    0.69
    Activations Density 0.018%

    No Known Activations