© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98758
    Prev
    Next
    INDEX
    Explanations

    initial quotes and periods identifying titles or snippets

    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
     perhaps
    -0.87
    模様
    -0.82
     biz
    -0.76
     whats
    -0.76
     Perhaps
    -0.75
     weird
    -0.74
     wasted
    -0.74
     dies
    -0.73
     groundwater
    -0.73
    ابل
    -0.72
    POSITIVE LOGITS
     Wp
    1.03
     WPS
    1.00
     wc
    0.99
     wb
    0.99
     WM
    0.98
     WG
    0.96
     WI
    0.96
     WN
    0.96
     WC
    0.95
     WU
    0.93
    Activations Density 1.279%

    No Known Activations