© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 766
    Prev
    Next
    INDEX
    Explanations

    conjunctions and foreign words

    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_10/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
    
    -1.50
    ✏️
    -1.47
     makinesi
    -1.45
    scrollPane
    -1.45
     that
    -1.45
    ↑
    -1.45
     nodo
    -1.43
    gestellt
    -1.42
    🆕
    -1.41
    ření
    -1.40
    POSITIVE LOGITS
     \
    2.02
     however
    1.90
    {
    1.84
    however
    1.84
     will
    1.52
    2
    1.51
    1
    1.48
     there
    1.38
     jedynie
    1.34
     многих
    1.31
    Activations Density 0.012%

    No Known Activations