Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110200
    Prev
    Next
    INDEX
    Explanations

    for loop variable `i`

    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
    lusst
    -0.91
    例文帳に追加
    -0.89
     mandiri
    -0.88
    alties
    -0.84
    âteau
    -0.83
    indiri
    -0.83
     Handlung
    -0.82
    あら
    -0.81
    专用
    -0.81
     lantaran
    -0.81
    POSITIVE LOGITS
     peo
    0.75
    ='';
    
    0.73
     {},
    
    0.71
    薙
    0.70
     insights
    0.69
     saw
    0.69
    هایی
    0.68
    みます
    0.68
     ansehen
    0.68
     Cod
    0.68
    Activations Density 0.003%

    No Known Activations