© 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. 34-GEMMASCOPE-RES-131K
    7. 109769
    Prev
    Next
    INDEX
    Explanations

    island basalts, East Rift

    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
    区间
    -0.90
    лле
    -0.79
     berlina
    -0.78
     небе
    -0.77
    վ
    -0.75
    cocho
    -0.73
    ciano
    -0.73
     стихотво
    -0.72
     Saskatoon
    -0.72
     минера
    -0.71
    POSITIVE LOGITS
    Accommodation
    0.87
     tuoi
    0.81
    րա
    0.81
     zalo
    0.81
    Roi
    0.80
    Oblig
    0.79
     sea
    0.78
     Accommodation
    0.76
     accommodation
    0.75
     drowned
    0.74
    Activations Density 0.014%

    No Known Activations