© 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. 32229
    Prev
    Next
    INDEX
    Explanations

    possessive 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_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
    Mine
    -0.93
     खुद
    -0.90
     poft
    -0.83
     multa
    -0.78
     copi
    -0.77
     complica
    -0.77
    lus
    -0.77
     anivers
    -0.75
     discrepan
    -0.74
    mine
    -0.74
    POSITIVE LOGITS
     their
    2.53
     his
    2.36
     your
    2.30
     our
    2.19
     its
    1.98
     my
    1.73
     swojego
    1.42
     swoje
    1.38
     swój
    1.36
     своего
    1.30
    Activations Density 0.134%

    No Known Activations