© 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. 74118
    Prev
    Next
    INDEX
    Explanations

    people, costs, and related roles

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

    people or beings followed by relative clauses

    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
    checker
    0.51
    user
    0.49
    跟
    0.48
    node
    0.48
    Entities
    0.47
    CurrentUser
    0.47
    Checker
    0.47
     เพื่อน
    0.47
    uploader
    0.45
    给
    0.45
    POSITIVE LOGITS
     którzy
    0.70
     وطالبات
    0.68
     الذين
    0.66
     ktorí
    0.66
     kteří
    0.61
     who
    0.57
     Their
    0.55
     അവരുടെ
    0.54
     quienes
    0.52
     அவர்களின்
    0.52
    Activations Density 0.230%

    No Known Activations