© 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. 58066
    Prev
    Next
    INDEX
    Explanations

    drilling mud and cuttings

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly responds to specialized oil-and-gas drilling terminology and measurements (e.g. well bores, cuttings, drilling fluids, hole cleaning).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ography
    -0.88
     Redeemer
    -0.77
     repellent
    -0.75
    scopes
    -0.73
    ーション
    -0.73
    orters
    -0.73
     супру
    -0.72
    bodyParser
    -0.72
    ylum
    -0.71
    纠结
    -0.71
    POSITIVE LOGITS
     drilling
    1.30
     mud
    1.26
     cuttings
    1.22
    Drilling
    1.12
     Mud
    1.08
     Drilling
    0.99
    mud
    0.99
     MUD
    0.96
     drill
    0.94
    Mud
    0.93
    Activations Density 0.058%

    No Known Activations