© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54643
    Prev
    Next
    INDEX
    Explanations

    beneath or underneath, often followed by "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_width_262k_l0_small_affine
    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
     podej
    0.39
     incurred
    0.37
     ವಿಧಾನ
    0.36
    胫
    0.35
    ೃ
    0.35
     বণ্টন
    0.35
    沾
    0.35
    龧
    0.35
    ደት
    0.35
     hours
    0.35
    POSITIVE LOGITS
     beneath
    0.78
     Beneath
    0.70
    behind
    0.68
    Behind
    0.68
     underneath
    0.68
     Behind
    0.65
     behind
    0.65
    Bene
    0.59
     detrás
    0.58
     dietro
    0.58
    Activations Density 0.025%

    No Known Activations