© 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. 29184
    Prev
    Next
    INDEX
    Explanations

    control, ownership, and belonging

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

    ownership or dominion

    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
     আয়াত
    0.44
     richieste
    0.43
     amounted
    0.43
     μεγ
    0.41
     জাহাজ
    0.41
    ҫ
    0.40
     critics
    0.40
    원본파일명
    0.39
     μεγά
    0.39
     imprese
    0.39
    POSITIVE LOGITS
     مستقل
    0.60
     pertence
    0.56
     pertenc
    0.54
     تابع
    0.53
    隶
    0.52
     controlled
    0.51
     autonomous
    0.50
     автоном
    0.50
     auton
    0.50
     Autonomous
    0.49
    Activations Density 0.036%

    No Known Activations