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. 8427
    Prev
    Next
    INDEX
    Explanations

    version numbers and email addresses

    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
     spolu
    -0.87
    vého
    -0.80
    istered
    -0.79
    kru
    -0.78
    あの
    -0.77
    reon
    -0.75
    minar
    -0.75
     Το
    -0.75
    bitol
    -0.75
     ELE
    -0.73
    POSITIVE LOGITS
    empres
    0.91
     השאלה
    0.90
    SÍ
    0.88
     kadang
    0.88
    zdjęcie
    0.86
     bazen
    0.85
    Ajust
    0.83
     maniere
    0.81
    番外
    0.80
    
    0.80
    Activations Density 0.043%

    No Known Activations