© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5867
    Prev
    Next
    INDEX
    Explanations

    referring to friends

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

    your friend

    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
     handler
    0.40
    सोई
    0.39
     Kxd
    0.38
    τζ
    0.37
     bổ
    0.36
     supremo
    0.36
     nrows
    0.36
    巌
    0.35
     subcluster
    0.35
    JsonKey
    0.35
    POSITIVE LOGITS
     friends
    4.03
    friends
    3.80
    朋友
    3.67
    Friends
    3.64
     친구
    3.61
     Friends
    3.48
    友人
    3.39
     friend
    3.34
     Freunde
    3.34
     друзья
    3.33
    Activations Density 0.160%

    No Known Activations