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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64772
    Prev
    Next
    INDEX
    Explanations

    our or we

    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
     vader
    -0.84
     Mural
    -0.81
     haue
    -0.79
    RAF
    -0.78
     IPCC
    -0.78
     jobber
    -0.78
     vhs
    -0.75
     byen
    -0.73
     Israelites
    -0.72
     PERT
    -0.71
    POSITIVE LOGITS
     we
    1.70
     our
    1.69
     naszej
    1.44
     нашем
    1.38
     unserer
    1.37
     naszych
    1.30
     Daily
    1.26
    我们
    1.18
     Gazette
    1.18
     нашей
    1.17
    Activations Density 0.255%

    No Known Activations