© 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. 60882
    Prev
    Next
    INDEX
    Explanations

    software licenses and technical terms

    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
     labouring
    -0.80
    rigley
    -0.78
    座
    -0.75
    綾
    -0.70
    atterns
    -0.68
     Koen
    -0.68
     laboring
    -0.67
    危
    -0.66
    urlpatterns
    -0.66
     lour
    -0.66
    POSITIVE LOGITS
     أعلام
    0.72
    qJ
    0.68
     expire
    0.67
    aram
    0.66
    Waters
    0.65
    阅
    0.65
     towel
    0.63
    𝓼
    0.63
     Highland
    0.62
    싶
    0.62
    Activations Density 0.054%

    No Known Activations