© 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. 16445
    Prev
    Next
    INDEX
    Explanations

    outsourcing activities and services

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

    replacing jobs or professions

    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
    他の
    0.46
    ೇವಿನ
    0.46
     associates
    0.45
    મિત
    0.45
     связана
    0.41
    ிருக்கிற
    0.41
    cadherin
    0.41
    蕤
    0.41
     anteced
    0.40
    あるいは
    0.40
    POSITIVE LOGITS
     เพียง
    0.50
     Međutim
    0.47
    ❌
    0.46
     nhưng
    0.44
    🤖
    0.44
     gastronomy
    0.43
     hehe
    0.43
     YoY
    0.42
     Minimalism
    0.42
    🦾
    0.42
    Activations Density 0.002%

    No Known Activations