© 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. 22-GEMMASCOPE-RES-131K
    7. 75197
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases with specific nouns

    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_22/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
    ⢊
    -1.23
     thuy
    -1.20
     and
    -1.19
    cepatan
    -1.14
     الخير
    -1.13
     nhat
    -1.12
     העולם
    -1.08
    
    -1.07
     Những
    -1.05
     gese
    -1.05
    POSITIVE LOGITS
    v
    1.40
     beschrieben
    1.27
     棒
    1.23
    ktion
    1.20
    n
    1.20
     different
    1.19
     δή
    1.19
     Different
    1.14
     festgestellt
    1.13
    譏
    1.13
    Activations Density 0.012%

    No Known Activations