© 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. 59519
    Prev
    Next
    INDEX
    Explanations

    SCADA systems

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

    This neuron specializes in picking out programming‐related tokens—especially code identifiers, file paths (e.g. include directives), class/namespace names, and similar technical symbols.

    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
     Diem
    -0.76
     diven
    -0.69
     conster
    -0.67
     تعط
    -0.67
     Exclusive
    -0.66
    cision
    -0.66
     illustre
    -0.65
    忍受
    -0.65
     فناوری
    -0.65
    西兰
    -0.63
    POSITIVE LOGITS
     Historian
    1.15
     historian
    1.06
     historians
    1.03
    OPC
    0.83
     wikipagina
    0.82
     MQTT
    0.82
     Kep
    0.82
     MES
    0.80
    Hist
    0.79
    Thing
    0.77
    Activations Density 0.033%

    No Known Activations