© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3087
    Prev
    Next
    INDEX
    Explanations

    trained professionals

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

    expert and skilled professionals

    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_53_width_65k_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
    ઐ
    0.42
     writable
    0.38
     nonatomic
    0.37
     ફરિયા
    0.35
     indah
    0.35
     keing
    0.35
    ϊ
    0.35
    찝
    0.35
     ት
    0.34
     বাধ
    0.34
    POSITIVE LOGITS
     skilled
    2.88
     experienced
    2.83
     expert
    2.58
     Experienced
    2.55
    Experienced
    2.52
    experienced
    2.50
    skilled
    2.48
     experts
    2.45
     전문가
    2.44
    expert
    2.39
    Activations Density 0.552%

    No Known Activations