© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11053
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

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

    your own

    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_40_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
    ogie
    0.48
    Фор
    0.47
    REGIUNE
    0.47
     வடி
    0.46
    ილი
    0.45
     चित्रित
    0.45
     decidedly
    0.44
    튼
    0.42
     admittedly
    0.42
    ado
    0.42
    POSITIVE LOGITS
     equipments
    0.58
     stuffs
    0.54
     another
    0.52
     advices
    0.51
     subordinates
    0.51
     incap
    0.48
     ANOTHER
    0.48
     peculiarity
    0.48
     NUE
    0.46
    തായ
    0.46
    Activations Density 0.303%

    No Known Activations