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. 8360
    Prev
    Next
    INDEX
    Explanations

    unity engine code

    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
    ]!='
    -0.79
    鴨
    -0.79
     Event
    -0.74
     MessageBoxIcon
    -0.71
    [{{
    -0.71
    ступ
    -0.71
     градусов
    -0.70
     overlook
    -0.70
    ]=="
    -0.70
     نسبت
    -0.69
    POSITIVE LOGITS
    Unity
    0.94
    Assets
    0.92
     Scripts
    0.89
    unity
    0.88
     Assets
    0.86
     unity
    0.85
     UNITY
    0.82
     Unity
    0.82
    UNITY
    0.78
     scripts
    0.77
    Activations Density 0.014%

    No Known Activations