© 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. 34628
    Prev
    Next
    INDEX
    Explanations

    leave, pay, holiday, school

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

    The neuron flags terminology associated with workplace rights and employment disputes (e.g. maternity, discrimination, harassment, leave, dismissal).

    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
     Nato
    -0.82
    ',\
    -0.81
     Signor
    -0.80
    /$',
    -0.76
    お気軽
    -0.75
     poética
    -0.73
     Telekom
    -0.73
     Suomi
    -0.73
    ')(
    -0.73
    有効
    -0.73
    POSITIVE LOGITS
     HAV
    0.88
    yaf
    0.84
    addSubview
    0.81
    renz
    0.81
    Agree
    0.79
    conducting
    0.79
     gad
    0.79
    中山
    0.78
     bloqueo
    0.77
    同意
    0.76
    Activations Density 0.010%

    No Known Activations