© 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. 116251
    Prev
    Next
    INDEX
    Explanations

    working with practices

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

    The neuron flags words related to work or employment (e.g., work, working, workers, job).

    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
    ეტ
    -1.04
     individualized
    -0.91
     Juris
    -0.85
    しましょう
    -0.81
    lectric
    -0.78
     lavoro
    -0.74
    مواد
    -0.73
    ciano
    -0.73
     anxiously
    -0.72
    qiang
    -0.71
    POSITIVE LOGITS
     practices
    0.89
    practices
    0.88
     Practices
    0.82
     pattern
    0.81
     patterns
    0.80
    isolate
    0.80
    roli
    0.77
     Институ
    0.76
    nyx
    0.75
    acijos
    0.74
    Activations Density 0.025%

    No Known Activations