© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215415
    Prev
    Next
    INDEX
    Explanations

    injection molding

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     :"
    0.45
     jig
    0.41
     Jig
    0.39
    Cutting
    0.39
     राइट
    0.38
    Nich
    0.38
     உர
    0.38
     ダン
    0.37
     jigs
    0.37
    裁
    0.37
    POSITIVE LOGITS
     gate
    0.54
     flow
    0.52
    flow
    0.50
     inject
    0.50
     gated
    0.50
     injection
    0.47
     mold
    0.46
    Gate
    0.45
     injected
    0.44
     gates
    0.43
    Activations Density 0.005%

    No Known Activations