© 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. 84634
    Prev
    Next
    INDEX
    Explanations

    programming keywords followed by punctuation

    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
     itself
    -1.06
     again
    -1.02
    民國
    -0.94
    urther
    -0.94
    ıca
    -0.94
     開催
    -0.91
    事です
    -0.90
     HomeScreen
    -0.90
    ～、
    -0.90
     this
    -0.89
    POSITIVE LOGITS
     pertama
    1.26
     first
    1.10
    erville
    1.09
    怎么了
    1.06
    Первый
    1.00
    auml
    0.98
     primera
    0.98
    气氛
    0.98
    Сейчас
    0.98
     primeros
    0.95
    Activations Density 0.054%

    No Known Activations