© 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. 60046
    Prev
    Next
    INDEX
    Explanations

    specialized phrases or abbreviations

    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
     citoyen
    -0.87
    र्श
    -0.86
     undersigned
    -0.84
     pursuance
    -0.84
     herewith
    -0.83
     poulet
    -0.82
    Legenda
    -0.81
     pertin
    -0.79
     chargé
    -0.79
     сыром
    -0.78
    POSITIVE LOGITS
    liciter
    1.05
    Neden
    1.04
    θρώ
    1.02
    TouchableOpacity
    0.95
    连接
    0.94
     xảy
    0.92
     buscar
    0.90
    测试
    0.89
     Professor
    0.89
     relied
    0.89
    Activations Density 0.008%

    No Known Activations