© 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. 81523
    Prev
    Next
    INDEX
    Explanations

    cross sectional views and figures

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

    The neuron detects references to illustrative figures or schematic views (e.g., “FIG,” figure numbers, “cross-sectional view,” “showing,” etc.).

    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
    Эзоҳ
    -0.74
    boxes
    -0.70
     برق
    -0.69
     Gillespie
    -0.69
    了许多
    -0.69
    场合
    -0.69
     어
    -0.68
     realm
    -0.68
    售价
    -0.68
    nologies
    -0.67
    POSITIVE LOGITS
     cross
    2.45
     sectional
    2.38
     exploded
    1.96
    cross
    1.88
    sectional
    1.88
     section
    1.81
     cut
    1.75
     Cross
    1.74
    Cross
    1.74
    CROSS
    1.70
    Activations Density 0.054%

    No Known Activations