© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 238
    Prev
    Next
    INDEX
    Explanations

    romantic relationships and flirtation

    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
     excre
    0.59
     genealogical
    0.58
     taxon
    0.56
    伉
    0.55
     iteratively
    0.55
    ogeneity
    0.54
     genealog
    0.54
     cryptographic
    0.54
     bereaved
    0.52
     nutritive
    0.52
    POSITIVE LOGITS
     boyfriend
    1.07
    boyfriend
    1.01
     Boyfriend
    0.95
     cute
    0.88
     cutest
    0.88
     Snapchat
    0.84
    💋
    0.83
     girly
    0.80
    男朋友
    0.77
     kisses
    0.75
    Activations Density 0.571%

    No Known Activations