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. 7958
    Prev
    Next
    INDEX
    Explanations

    Public keys and names

    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
     this
    -0.87
     עבור
    -0.80
    DISCUSSION
    -0.77
     прия
    -0.77
    Ведь
    -0.76
    روابط
    -0.76
    atillas
    -0.76
     for
    -0.75
    쯔
    -0.72
     enjoyment
    -0.72
    POSITIVE LOGITS
     //
    0.90
    ícia
    0.82
    “[
    0.80
     ۱۳۸
    0.79
    Consistent
    0.79
    drawString
    0.79
    störungen
    0.79
     Ռ
    0.79
    lamps
    0.79
    glieder
    0.78
    Activations Density 0.001%

    No Known Activations