© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 209024
    Prev
    Next
    INDEX
    Explanations

    feeling/sense

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     S
    1.95
     الس
    1.47
    S
    1.23
     স
    1.20
    <0xAF>
    1.05
     הס
    1.05
    Ｓ
    0.97
     س
    0.93
     С
    0.92
    الس
    0.90
    POSITIVE LOGITS
     feeling
    1.52
    感觉
    1.48
     feel
    1.45
    feeling
    1.45
     gevoel
    1.45
    feel
    1.41
    Feel
    1.40
    感覺
    1.39
     Feel
    1.38
     чув
    1.34
    Activations Density 0.005%

    No Known Activations