© 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. 22969
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

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

    self-knowledge and personal reflection

    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
     পরিচিত
    0.41
    нең
    0.39
     Middleware
    0.39
    퍽
    0.39
     Apr
    0.38
     চারি
    0.38
    괜
    0.38
    зг
    0.37
     বিপ্ল
    0.37
     Incorporation
    0.37
    POSITIVE LOGITS
     নিজেও
    1.05
     himself
    0.85
     themselves
    0.77
    我自己
    0.74
     खुद
    0.73
    自身
    0.72
    ตัวเอง
    0.71
     herself
    0.70
     स्वयं
    0.69
     ourselves
    0.68
    Activations Density 0.063%

    No Known Activations