© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11761
    Prev
    Next
    INDEX
    Explanations

    socializing

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

    social

    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_40_width_16k_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
     unilaterally
    0.42
     بيد
    0.41
     المض
    0.37
     rembour
    0.35
     calma
    0.35
     unfl
    0.35
     මෙ
    0.35
    尃
    0.35
     padding
    0.34
     তিনিই
    0.34
    POSITIVE LOGITS
    社交
    1.88
     socializing
    1.83
     socialize
    1.82
     socialization
    1.75
     social
    1.72
     sociable
    1.70
    social
    1.66
     networking
    1.63
     sociale
    1.59
     sociali
    1.59
    Activations Density 0.556%

    No Known Activations