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. 8207
    Prev
    Next
    INDEX
    Explanations

    Content-Type header

    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
     content
    -0.82
    コンテンツ
    -0.77
    content
    -0.73
    Content
    -0.72
     قطاع
    -0.71
    atrième
    -0.71
    ceded
    -0.70
     Mounts
    -0.69
     сред
    -0.67
     المحت
    -0.66
    POSITIVE LOGITS
     type
    2.13
    type
    1.99
     Type
    1.98
    Type
    1.80
    TYPE
    1.73
     types
    1.71
     TYPE
    1.68
     Types
    1.53
    types
    1.53
    Types
    1.46
    Activations Density 0.055%

    No Known Activations