© 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. 102893
    Prev
    Next
    INDEX
    Explanations

    training programs and courses

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

    The neuron strongly activates on instances of the word “training,” i.e. references to instructional or educational programs.

    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
     tanul
    -0.94
     Bier
    -0.82
     Guilford
    -0.79
     mieten
    -0.76
     hai
    -0.76
     Coding
    -0.73
    に挑戦
    -0.73
    three
    -0.72
     daily
    -0.72
    죠
    -0.72
    POSITIVE LOGITS
     programs
    1.48
     programmes
    1.38
    programs
    1.31
     program
    1.27
     programas
    1.21
     Programs
    1.19
     programu
    1.13
    Programs
    1.13
     PROGRAMS
    1.05
     provider
    1.03
    Activations Density 0.022%

    No Known Activations