© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11500
    Prev
    Next
    INDEX
    Explanations

    fortunately, thankfully, luckily

    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_22/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
    ㅛ
    -0.92
     bahkan
    -0.91
    []){
    -0.85
    owski
    -0.83
     menyiapkan
    -0.83
    siah
    -0.82
    ubmit
    -0.82
     even
    -0.82
    משך
    -0.81
     даже
    -0.80
    POSITIVE LOGITS
     fortunately
    1.52
     thankfully
    1.41
     luckily
    1.32
    Fortunately
    1.27
     Fortunately
    1.21
    fortunately
    1.14
    Thankfully
    1.11
    Luckily
    1.03
     safe
    1.02
     Luckily
    1.02
    Activations Density 0.091%

    No Known Activations