© 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. 92426
    Prev
    Next
    INDEX
    Explanations

    reviewing and assessing information

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

    The neuron strongly activates on words in document titles, headings, or other section‐header text (e.g. title‐case or all‐caps phrases).

    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
     Monitoring
    -1.02
    ͆
    -0.88
    monitoring
    -0.88
     monitore
    -0.88
    测量
    -0.86
     Measurements
    -0.86
     monitored
    -0.85
    monitor
    -0.85
     Monitor
    -0.85
    zyk
    -0.85
    POSITIVE LOGITS
     desk
    1.57
     desktop
    1.55
     interviews
    1.46
    desktop
    1.32
     review
    1.27
     Desk
    1.20
     meetings
    1.16
     fieldwork
    1.15
     literature
    1.10
     expert
    1.10
    Activations Density 0.040%

    No Known Activations