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. 8357
    Prev
    Next
    INDEX
    Explanations

    date ranges, television series

    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
    liehen
    -0.86
    Informationen
    -0.85
    Obsah
    -0.84
    刧
    -0.79
     cumbersome
    -0.79
     Informações
    -0.79
    Cursed
    -0.79
    Cordial
    -0.78
    Robust
    -0.76
    urtstag
    -0.76
    POSITIVE LOGITS
    StructEnd
    1.00
     akar
    0.84
     dict
    0.84
     Pal
    0.79
     Ains
    0.78
    ook
    0.76
    語
    0.75
     clay
    0.75
     glass
    0.74
     RegExp
    0.73
    Activations Density 0.048%

    No Known Activations