© 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. 90314
    Prev
    Next
    INDEX
    Explanations

    geological faults and fractures

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

    This neuron detects terms related to geological faults and plate tectonics (e.g. “fault lines,” shifting plates).

    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
     circumscribed
    -0.82
     дорог
    -0.78
    ौर
    -0.77
    影视
    -0.77
     moored
    -0.76
    воз
    -0.75
    ToFit
    -0.74
    扁
    -0.74
     Miao
    -0.74
     shapes
    -0.73
    POSITIVE LOGITS
     fault
    2.17
     Fault
    1.94
     faults
    1.91
    fault
    1.70
    Fault
    1.63
    FAULT
    1.30
     faut
    1.16
    faults
    1.05
     Offset
    1.02
    Faults
    1.02
    Activations Density 0.009%

    No Known Activations