© 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. 109695
    Prev
    Next
    INDEX
    Explanations

    Caribbean, Central American, and South American places

    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
     campan
    -0.86
     Aleppo
    -0.82
    BELL
    -0.81
     estudos
    -0.79
     TANK
    -0.76
     importe
    -0.75
    ExceptionHandler
    -0.74
    Inference
    -0.73
     bell
    -0.73
     industriales
    -0.73
    POSITIVE LOGITS
     braids
    0.82
     Jamaican
    0.73
    Hair
    0.69
     curry
    0.66
     Afro
    0.66
     influence
    0.66
    Along
    0.66
    olato
    0.66
     Along
    0.65
    ーズ
    0.65
    Activations Density 0.013%

    No Known Activations