© 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. 12597
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns and "self"

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

    reflexive pronouns and their actions

    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
     তোমাকে
    0.53
     serán
    0.51
     gesprochen
    0.51
    nms
    0.50
     fehlen
    0.50
     mancanza
    0.50
    ɲ
    0.49
    porcion
    0.49
     reducido
    0.49
     individus
    0.48
    POSITIVE LOGITS
    self
    0.54
    selves
    0.54
     self
    0.50
     Self
    0.47
    ſelf
    0.46
     sendiri
    0.46
     Fayette
    0.45
     AGAINST
    0.44
     själv
    0.44
      
    0.43
    Activations Density 0.090%

    No Known Activations