© 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. 17328
    Prev
    Next
    INDEX
    Explanations

    friends, mates, acquaintances

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

    social connections and acquaintances

    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
     مشتری
    0.41
     коммуника
    0.39
    稦
    0.39
     Boundaries
    0.39
    淢
    0.38
     BATH
    0.38
     почув
    0.38
     নিকটে
    0.38
     お客様
    0.38
     星
    0.37
    POSITIVE LOGITS
     friends
    0.66
    friends
    0.65
    friend
    0.59
    Friends
    0.55
    友人
    0.55
    Friend
    0.54
     друзья
    0.54
     Freunde
    0.54
    朋友
    0.53
     friend
    0.52
    Activations Density 0.098%

    No Known Activations