© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65802
    Prev
    Next
    INDEX
    Explanations

    twelve

    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
    VII
    -0.77
    XV
    -0.77
    Developer
    -0.74
    Teenage
    -0.72
    QUESTION
    -0.70
     vlož
    -0.69
     Teenage
    -0.69
    Somalia
    -0.69
     AUGUST
    -0.68
    十七
    -0.68
    POSITIVE LOGITS
     twelve
    1.34
     Twelve
    1.29
    twelve
    1.23
    Twelve
    1.17
     douze
    1.08
     doce
    1.05
     ۱۲
    1.03
    十二
    1.01
    ۱۲
    0.98
     twelfth
    0.94
    Activations Density 0.087%

    No Known Activations