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. 8139
    Prev
    Next
    INDEX
    Explanations

    fill in blanks

    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
    宝贝
    -0.79
    plastik
    -0.75
    ichtet
    -0.74
     dü
    -0.74
     lynch
    -0.73
    
    -0.73
    ρυσ
    -0.72
     sàn
    -0.71
    佐々木
    -0.68
    ieras
    -0.68
    POSITIVE LOGITS
     fill
    4.28
    fill
    3.70
     Fill
    3.64
    Fill
    3.36
     blanks
    3.16
     filling
    3.11
    FILL
    3.00
     fills
    2.95
     blank
    2.86
     FILL
    2.83
    Activations Density 0.069%

    No Known Activations