© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2080
    Prev
    Next
    INDEX
    Explanations

    building connection and intimacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    自分で
    0.53
     zbior
    0.42
    覆盖
    0.37
    aggregate
    0.37
    раи
    0.36
     Recursive
    0.36
    稼
    0.36
     ضر
    0.35
    ოდ
    0.35
     granularity
    0.35
    POSITIVE LOGITS
     friendship
    1.28
     intimacy
    1.26
     mutual
    1.23
     bonding
    1.16
     relationship
    1.12
    mutual
    1.11
     amistad
    1.06
    Mutual
    1.03
     Mutual
    1.02
    互相
    1.01
    Activations Density 1.033%

    No Known Activations