© 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. 53-GEMMASCOPE-2-RES-262K
    7. 40994
    Prev
    Next
    INDEX
    Explanations

    sacrum and pelvis

    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/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Neck
    0.58
     neck
    0.54
    Neck
    0.54
    颈
    0.48
     sleeve
    0.46
     sleeves
    0.45
     Sleeve
    0.45
    袖
    0.44
    neck
    0.43
     forearm
    0.41
    POSITIVE LOGITS
     sac
    1.19
     Sac
    1.13
    Sac
    1.09
    sac
    1.01
     pelvic
    0.94
     pub
    0.93
     sacro
    0.91
     SAC
    0.86
    骶
    0.84
     pelvis
    0.82
    Activations Density 0.014%

    No Known Activations