© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8421
    Prev
    Next
    INDEX
    Explanations

    my possessions and relationships

    np_acts-logits-general · gemini-2.5-flash-lite

    possessive pronoun followed by personal attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    0.36
     their
    0.27
    各自
    0.25
    y
    0.25
    aing
    0.25
    a
    0.24
    upon
    0.24
    im
    0.23
    s
    0.23
    your
    0.23
    POSITIVE LOGITS
     करियर
    0.31
     мои
    0.30
     خودم
    0.30
     ജീവിത
    0.29
     নিজের
    0.28
     дітей
    0.28
     twenties
    0.27
     Familie
    0.27
     мою
    0.27
     জীবনে
    0.26
    Activations Density 0.681%

    No Known Activations