© 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. 93890
    Prev
    Next
    INDEX
    Explanations

    gig related words

    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
    hbs
    -0.76
    ม้
    -0.75
    ヌ
    -0.75
     diversity
    -0.72
     perfect
    -0.71
     guard
    -0.71
    ၆
    -0.71
     Plains
    -0.70
     controlled
    -0.69
     Sonne
    -0.69
    POSITIVE LOGITS
     Gig
    1.45
     gig
    1.34
    Gig
    1.24
    gig
    1.16
     GIG
    1.10
     gigs
    0.99
     Hadid
    0.91
    antic
    0.88
    unset
    0.84
     ̄)
    0.84
    Activations Density 0.009%

    No Known Activations