© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109879
    Prev
    Next
    INDEX
    Explanations

    WWE wrestling events and talent

    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
    圏
    -0.77
     two
    -0.76
     Каза
    -0.72
    康熙
    -0.72
     org
    -0.70
     hated
    -0.69
     p
    -0.69
     Ex
    -0.69
     og
    -0.69
     webs
    -0.69
    POSITIVE LOGITS
     الاقتصاد
    0.88
     Shield
    0.84
     Tommaso
    0.79
    WWE
    0.79
    Shield
    0.78
    ⏯
    0.77
    ឋ
    0.76
     komentar
    0.75
    EXTR
    0.75
    ConstraintLayout
    0.75
    Activations Density 0.010%

    No Known Activations