© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108080
    Prev
    Next
    INDEX
    Explanations

    owned media

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

    emotional connections and attraction

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    🫢
    0.49
    ánea
    0.44
    cached
    0.43
     mistaken
    0.41
    truncated
    0.40
     سامنا
    0.40
    unsplash
    0.40
    🫤
    0.40
     সমাপ্ত
    0.40
    major
    0.39
    POSITIVE LOGITS
    爱
    0.45
    将
    0.44
    帮
    0.43
    愛
    0.42
     అయితే
    0.41
    ंदरे
    0.41
     ஊக்கு
    0.41
    妒
    0.40
     eftersom
    0.40
    动画
    0.39
    Activations Density 0.001%

    No Known Activations