© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21587
    Prev
    Next
    INDEX
    Explanations

    emoji

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    銳
    0.44
    ICs
    0.43
     ohmic
    0.43
     vésicules
    0.42
     veineux
    0.40
     গবে
    0.39
     phy
    0.39
    shrink
    0.39
    Ic
    0.39
    _<
    0.39
    POSITIVE LOGITS
     emoji
    0.96
     Emoji
    0.94
     emojis
    0.88
    emoji
    0.76
    Emoji
    0.75
    Emojis
    0.71
    ️
    0.50
     इमो
    0.49
     Joining
    0.47
     ‍
    0.47
    Activations Density 0.006%

    No Known Activations