© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118044
    Prev
    Next
    INDEX
    Explanations

    skilled professionals

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

    The neuron strongly activates on numeric values and quantifying expressions (e.g. raw numbers and words indicating amounts).

    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
     Patients
    -1.05
     pacientes
    -1.05
    Patients
    -1.02
    patients
    -0.95
    Passengers
    -0.93
     Kunden
    -0.91
     espectador
    -0.90
     paciente
    -0.90
    dagogik
    -0.89
     diners
    -0.89
    POSITIVE LOGITS
     staff
    3.67
     personnel
    3.41
     skilled
    3.08
     talented
    2.80
     trained
    2.70
     professionals
    2.58
     experienced
    2.50
    staff
    2.48
     specialists
    2.39
     experts
    2.34
    Activations Density 0.136%

    No Known Activations