© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93016
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by creative works

    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
     Data
    -0.84
     tudi
    -0.83
     Operations
    -0.81
     mężczyzn
    -0.79
     filmmakers
    -0.79
     है
    -0.78
     composers
    -0.75
    了不少
    -0.75
    inities
    -0.75
     dezelfde
    -0.74
    POSITIVE LOGITS
     work
    2.66
     creations
    2.33
     works
    2.05
     writings
    1.84
     products
    1.80
    作品
    1.76
     stuff
    1.57
     output
    1.55
     designs
    1.48
     songs
    1.47
    Activations Density 0.075%

    No Known Activations