© 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. 116064
    Prev
    Next
    INDEX
    Explanations

    but, however, although

    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
     anyway
    -1.13
    therefore
    -1.12
     dát
    -1.10
    tissimi
    -1.05
     поэтому
    -1.04
    пів
    -1.04
     quindi
    -1.02
     ráp
    -1.02
     therefore
    -1.02
     yes
    -1.01
    POSITIVE LOGITS
     there
    2.00
     not
    1.54
    并不是
    1.39
     merely
    1.34
    并非
    1.23
     equally
    1.22
     cautioned
    1.22
    並不是
    1.19
    While
    1.16
     despite
    1.13
    Activations Density 0.094%

    No Known Activations