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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109945
    Prev
    Next
    INDEX
    Explanations

    UNESCO conventions and assemblies

    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
     zelf
    -0.79
     Román
    -0.75
    戚
    -0.74
    ᅠ
    -0.73
     agosto
    -0.72
    >>();
    -0.72
     England
    -0.71
    谿
    -0.69
    FOREIGN
    -0.69
    旅客
    -0.68
    POSITIVE LOGITS
     UNESCO
    2.88
    UNESCO
    2.38
     Unesco
    1.88
    unes
    1.27
     Courier
    0.91
    esco
    0.88
    Courier
    0.84
    enschappen
    0.82
    ICOM
    0.81
    ESCO
    0.81
    Activations Density 0.007%

    No Known Activations