© 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. 48148
    Prev
    Next
    INDEX
    Explanations

    workplace aspects and environment

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

    The neuron strongly activates on occurrences of the word “workplace,” i.e. it detects mentions of workplace contexts.

    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
    pushFollow
    -0.83
     understatement
    -0.80
     volup
    -0.80
    ਆ
    -0.79
     prickly
    -0.76
     Notation
    -0.75
    <>
    -0.75
    resultMap
    -0.75
    ()};
    -0.74
     работы
    -0.72
    POSITIVE LOGITS
     injury
    0.93
     diversity
    0.91
    place
    0.90
     bullying
    0.89
     environment
    0.89
     dynamics
    0.89
     Erben
    0.84
     place
    0.83
     environments
    0.83
     miejsce
    0.82
    Activations Density 0.014%

    No Known Activations