© 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. 59197
    Prev
    Next
    INDEX
    Explanations

    skills and experience application

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

    The neuron detects terminology associated with educational or training programs—words like course, certification, dives, skills, learning, and knowledge.

    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
     for
    -1.39
    When
    -1.23
    了
    -1.20
     now
    -1.20
     when
    -1.19
     because
    -1.19
     your
    -1.18
     acogedor
    -1.16
     vanwege
    -1.16
     it
    -1.12
    POSITIVE LOGITS
     while
    2.45
     mereka
    1.87
     mientras
    1.74
     whilst
    1.74
     WHILE
    1.70
    while
    1.65
     they
    1.57
     mentre
    1.52
    他們
    1.45
     sambil
    1.42
    Activations Density 0.065%

    No Known Activations