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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17747
    Prev
    Next
    INDEX
    Explanations

    quartz crystal minerals gemology

    np_acts-logits-general · gemini-2.5-flash-lite

    gemstone descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Conservative
    0.52
    
    0.45
     conservatism
    0.44
    娼
    0.44
     Conservatives
    0.42
     ресторан
    0.42
    мб
    0.42
    资
    0.42
     Conservative
    0.42
    สัญญา
    0.41
    POSITIVE LOGITS
     specimens
    1.10
     crystals
    1.09
     specimen
    1.06
     gemstone
    1.02
     crystal
    1.00
     calcite
    0.99
     gem
    0.96
     mineral
    0.95
     gemstones
    0.93
     crystalline
    0.91
    Activations Density 0.081%

    No Known Activations