© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 10915
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_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
     রহিয়াছে
    0.69
     fractures
    0.68
     served
    0.63
     storied
    0.62
     ಒಂದು
    0.62
    殇
    0.62
    これは
    0.61
     disrupted
    0.61
     clouds
    0.59
     perforated
    0.59
    POSITIVE LOGITS
     him
    1.30
     you
    1.10
     swojej
    1.02
     তাকে
    0.99
     вас
    0.99
     ihn
    0.99
     आप
    0.98
    他的
    0.96
    你
    0.95
     us
    0.95
    Activations Density 0.014%

    No Known Activations