© 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. 10-GEMMASCOPE-RES-131K
    7. 59963
    Prev
    Next
    INDEX
    Explanations

    facing [direction/object]

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

    The neuron specifically detects occurrences of the word “facing,” whether used literally (e.g. south-facing) or metaphorically (e.g. customer-facing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -2.55
    や
    -2.50
    
    -2.41
    ⇴
    -2.16
    z
    -2.14
    </i>
    -2.09
    ведите
    -2.05
     aspire
    -2.05
    ugeot
    -2.02
    НЫЕ
    -2.02
    POSITIVE LOGITS
     facing
    3.02
    a
    2.81
    此前
    2.80
    
    2.66
     the
    2.64
     одежда
    2.38
    ⟝
    2.33
    ︲
    2.31
    罴
    2.31
    晅
    2.28
    Activations Density 0.004%

    No Known Activations