© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64287
    Prev
    Next
    INDEX
    Explanations

    sewing and making things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Engraved
    -0.77
    urities
    -0.75
    ptures
    -0.73
     biotechnology
    -0.71
    敖
    -0.69
     []:
    -0.68
     engraved
    -0.68
     débar
    -0.68
     smeared
    -0.67
    ポーズ
    -0.67
    POSITIVE LOGITS
     sewing
    4.31
     sew
    3.42
    Sew
    3.38
     Sewing
    3.38
    sewing
    3.06
     sewn
    3.03
     Sew
    2.91
     stitching
    2.83
     sewed
    2.78
     stitch
    2.59
    Activations Density 0.089%

    No Known Activations