© 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. 110540
    Prev
    Next
    INDEX
    Explanations

    quartz and crystals

    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
    viewDid
    -0.90
    wakeup
    -0.89
    šiu
    -0.83
    pfn
    -0.79
    Sultan
    -0.78
     notepad
    -0.78
    pFile
    -0.77
    tifical
    -0.75
     Lumber
    -0.72
    めに
    -0.70
    POSITIVE LOGITS
     quartz
    1.19
     Quartz
    0.93
     crystal
    0.89
     QUART
    0.82
     crystals
    0.80
    hearted
    0.77
    水晶
    0.74
     quarts
    0.73
     agate
    0.73
     lens
    0.72
    Activations Density 0.017%

    No Known Activations