© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1177
    Prev
    Next
    INDEX
    Explanations

    underground mining

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

    This neuron detects terminology related to underground mine support (e.g. grout bags, mine roof support).

    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
     ironing
    -0.82
    Processing
    -0.77
    saat
    -0.75
     Ohl
    -0.75
    isant
    -0.75
     cấu
    -0.74
    processing
    -0.73
    ൺ
    -0.73
    tür
    -0.73
    Micros
    -0.72
    POSITIVE LOGITS
     underground
    1.70
     mine
    1.49
    underground
    1.35
     Underground
    1.21
    Underground
    1.17
     Mine
    1.17
     mining
    1.16
     miners
    1.14
     coal
    1.13
    Mine
    1.13
    Activations Density 0.036%

    No Known Activations