© 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. 84305
    Prev
    Next
    INDEX
    Explanations

    vice versa and conjunctions

    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
     impresa
    -0.99
     gegebenen
    -0.92
     comparable
    -0.89
     evidentemente
    -0.84
     vorgesch
    -0.81
     alimentazione
    -0.79
     möglicherweise
    -0.79
     boste
    -0.78
    頑張って
    -0.77
     nearby
    -0.77
    POSITIVE LOGITS
     vice
    2.06
    vice
    1.51
     viceversa
    1.36
     Vice
    1.28
    Vice
    1.20
     both
    1.09
     begge
    1.02
     vise
    1.00
     atau
    0.99
     दोनों
    0.98
    Activations Density 0.057%

    No Known Activations