© 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. 22-GEMMASCOPE-RES-131K
    7. 26027
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by personal thoughts

    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
     is
    -1.48
    niere
    -1.19
     คือ
    -1.11
     tersebut
    -1.10
    但却
    -1.04
     atriz
    -1.04
    ço
    -1.04
     me
    -1.01
    omitempty
    -1.00
    囯
    -1.00
    POSITIVE LOGITS
     thoughts
    1.51
     how
    1.41
     opinions
    1.32
     experiences
    1.30
     thinks
    1.20
     papai
    1.10
     views
    1.09
    źródło
    1.09
     pão
    1.07
     aranha
    1.07
    Activations Density 0.033%

    No Known Activations