© 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. 130560
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and objects

    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
    这让
    -0.94
    但这
    -0.91
    但她
    -0.90
    ポテト
    -0.88
    орты
    -0.86
     dessa
    -0.85
    слава
    -0.85
     desse
    -0.85
    koa
    -0.80
     mukaan
    -0.79
    POSITIVE LOGITS
     their
    2.52
     its
    2.22
     him
    1.93
     them
    1.89
     they
    1.83
     his
    1.65
     themselves
    1.57
    他们
    1.52
     itself
    1.48
     theirs
    1.40
    Activations Density 0.194%

    No Known Activations