© 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-262K
    7. 197
    Prev
    Next
    INDEX
    Explanations

    kisses and cuddles

    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_262k_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
    娯
    0.47
    뷁
    0.46
    豁
    0.44
    buckets
    0.43
    㗊
    0.42
    苛
    0.41
    欝
    0.40
     spinoff
    0.40
    槓
    0.40
    푯
    0.40
    POSITIVE LOGITS
     kisses
    1.30
     kiss
    1.18
     kissed
    1.16
     kissing
    1.13
     cuddling
    1.12
     cuddle
    1.07
     intimacy
    1.02
    kiss
    1.02
     intimate
    0.98
    Kiss
    0.98
    Activations Density 0.105%

    No Known Activations