© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11264
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by personal domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ோ
    2.37
    裘
    1.91
    ive
    1.89
    ivel
    1.88
    which
    1.87
    ால்
    1.86
    jected
    1.82
    el
    1.80
    ী
    1.78
    ism
    1.77
    POSITIVE LOGITS
     "${
    1.92
    Sit
    1.80
     titt
    1.79
     गेंदबाज
    1.78
    ameva
    1.78
    ्रेन
    1.77
    नवीन
    1.75
     Inst
    1.75
    Rip
    1.74
     Benefit
    1.74
    Activations Density 0.067%

    No Known Activations