© 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-16K
    7. 12489
    Prev
    Next
    INDEX
    Explanations

    physical affection and closeness

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

    tactile affection 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-pt/resid_post/layer_31_width_16k_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
     obser
    0.46
     لوا
    0.45
     rebut
    0.45
     renseignements
    0.41
     نسل
    0.41
    瞟
    0.41
     osserv
    0.41
    ிருப்ப
    0.40
    lexer
    0.40
     poker
    0.40
    POSITIVE LOGITS
     abrazo
    0.62
    抱
    0.61
     Kiss
    0.59
     kissing
    0.57
     Touching
    0.57
     hugged
    0.57
     hugging
    0.56
     kissed
    0.56
     hugs
    0.56
     cuddling
    0.56
    Activations Density 0.248%

    No Known Activations