© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66086
    Prev
    Next
    INDEX
    Explanations

    drill / drilling / drilled

    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_41_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
     Liquor
    0.39
     অত
    0.38
     aconte
    0.37
    觞
    0.37
     Vat
    0.37
     clickView
    0.37
    țile
    0.36
     batted
    0.36
    িনায়ক
    0.36
     pendiente
    0.35
    POSITIVE LOGITS
     drill
    1.42
     drilling
    1.34
    钻
    1.23
     Drill
    1.23
     drills
    1.20
    drill
    1.19
     Drilling
    1.15
     ड्रिल
    1.14
     drilled
    1.12
    鑽
    1.00
    Activations Density 0.001%

    No Known Activations