© 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. 118468
    Prev
    Next
    INDEX
    Explanations

    patent numbers and codes

    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
    ="/"
    -0.87
     or
    -0.85
    豉
    -0.77
    bestos
    -0.75
    {"{
    -0.75
    mitir
    -0.73
    閏
    -0.73
    يران
    -0.73
    sourceMap
    -0.72
    しゅ
    -0.72
    POSITIVE LOGITS
     seules
    0.94
    hez
    0.88
    ⣉
    0.81
    ITU
    0.80
    分けて
    0.80
     dore
    0.79
     俺
    0.78
    ѵ
    0.78
     américains
    0.78
    xii
    0.78
    Activations Density 0.012%

    No Known Activations