© 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. 9539
    Prev
    Next
    INDEX
    Explanations

    third-person pronouns

    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
     нашем
    -1.03
     our
    -1.01
     I
    -1.00
     nosso
    -0.99
    ,
    -0.98
     nossos
    -0.98
     unseres
    -0.92
     unserer
    -0.91
    леге
    -0.90
     нашего
    -0.87
    POSITIVE LOGITS
     personally
    1.20
     himself
    1.15
    themselves
    1.13
    himself
    1.12
     themselves
    1.07
    zelf
    1.00
     dirinya
    0.97
    自身
    0.96
    itself
    0.95
    自己
    0.95
    Activations Density 0.042%

    No Known Activations