© 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. 4287
    Prev
    Next
    INDEX
    Explanations

    in cooperation partnership conjunction

    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
    standers
    -0.96
    vece
    -0.92
     sarcastic
    -0.88
     sendok
    -0.83
    stander
    -0.82
    APPLAUSE
    -0.80
    Awkward
    -0.80
     chăm
    -0.80
    indest
    -0.79
     realizará
    -0.78
    POSITIVE LOGITS
     collaboration
    4.97
     partnership
    4.56
     cooperation
    4.06
    collaboration
    3.44
     collaborations
    3.42
     conjunction
    3.33
     Collaboration
    3.11
     сотрудни
    3.08
    Collaboration
    3.06
    partnership
    3.06
    Activations Density 0.105%

    No Known Activations