© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 80
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    They
    1.17
    These
    1.02
     delas
    1.01
    -
    1.01
     lidí
    1.00
     of
    0.98
     They
    0.98
    에서
    0.95
    We
    0.94
    *
    0.93
    POSITIVE LOGITS
     own
    1.85
     propre
    1.45
     propres
    1.44
     newfound
    1.38
     skillset
    1.35
     OWN
    1.35
     ability
    1.25
     innermost
    1.25
     plight
    1.25
     inability
    1.23
    Activations Density 1.674%

    No Known Activations