© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8811
    Prev
    Next
    INDEX
    Explanations

    social and interpersonal connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     elegan
    0.71
     calmly
    0.68
     calm
    0.67
     equal
    0.66
    ंपरिक
    0.66
     دیک
    0.64
     ছেলের
    0.62
    ̖
    0.60
     उमेश
    0.60
     calming
    0.60
    POSITIVE LOGITS
     friendships
    2.23
     relationships
    1.92
     Relationships
    1.81
    relationships
    1.77
    Relationships
    1.75
     acquaintances
    1.68
     Contacts
    1.67
    社交
    1.65
     contacts
    1.64
     Interactions
    1.61
    Activations Density 0.267%

    No Known Activations