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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118585
    Prev
    Next
    INDEX
    Explanations

    drilling and bore holes

    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
    attacks
    -0.85
    chats
    -0.78
    Przypisy
    -0.78
     onChange
    -0.77
     mariée
    -0.75
     repas
    -0.75
     عليكم
    -0.75
    👐
    -0.75
     Topping
    -0.74
    hatch
    -0.73
    POSITIVE LOGITS
     drilling
    3.95
     drill
    3.70
     drilled
    3.34
     Drilling
    2.91
     Drill
    2.91
    drill
    2.86
    Drill
    2.81
    Drilling
    2.70
     drills
    2.69
     bore
    2.36
    Activations Density 0.058%

    No Known Activations