© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 639
    Prev
    Next
    INDEX
    Explanations

    pronouns and associated actions/experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_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
     itself
    0.24
     собі
    0.23
    N
    0.21
     themselves
    0.21
    自分
    0.21
    W
    0.21
    sp
    0.21
    -
    0.20
    ak
    0.20
    CH
    0.20
    POSITIVE LOGITS
     personally
    0.28
    zelf
    0.26
     personalmente
    0.25
     deewana
    0.24
     جميعا
    0.23
    ſelf
    0.23
    Personally
    0.21
    哋
    0.21
    esterly
    0.21
     Personally
    0.21
    Activations Density 0.379%

    No Known Activations