© 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. 20533
    Prev
    Next
    INDEX
    Explanations

    fellow members of a group

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

    fellow people

    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
    й
    0.62
    ן
    0.61
    م
    0.57
    ق
    0.56
    ח
    0.55
    ч
    0.54
    ד
    0.53
    د
    0.51
    ي
    0.50
    מ
    0.50
    POSITIVE LOGITS
     compatriots
    0.62
     countrymen
    0.60
     fellow
    0.59
     peers
    0.56
     classmate
    0.53
    同期
    0.47
     teammate
    0.46
     classmates
    0.46
    เดียวกัน
    0.45
     Concurrent
    0.45
    Activations Density 0.035%

    No Known Activations