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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49269
    Prev
    Next
    INDEX
    Explanations

    trade shows, fairs, and expos

    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
    原始内容存档于
    -0.73
    يسة
    -0.73
     verhaal
    -0.71
     Sahne
    -0.68
     zwycię
    -0.67
     Griechen
    -0.66
    ノー
    -0.66
     Mour
    -0.66
     chuy
    -0.66
    grp
    -0.64
    POSITIVE LOGITS
     trade
    2.11
     expo
    1.98
     fair
    1.85
     fairs
    1.83
     exhibition
    1.83
     trades
    1.81
     exposition
    1.55
    trades
    1.55
     exhibitions
    1.55
     Expo
    1.55
    Activations Density 0.053%

    No Known Activations