© 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. 22-GEMMASCOPE-RES-131K
    7. 13465
    Prev
    Next
    INDEX
    Explanations

    the state of being left

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

    The neuron detects uses of the verb “leave” (in forms like “leaves” or “leaving”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    s
    -2.33
    4
    -2.08
    6
    -2.03
    .
    -2.00
    u
    -1.88
    1
    -1.87
    3
    -1.84
     货
    -1.73
     بداية
    -1.71
    餮
    -1.67
    POSITIVE LOGITS
     Popis
    1.95
    
    1.93
     indelible
    1.86
    🖱
    1.75
    淦
    1.66
    の方法
    1.64
    udnio
    1.64
     universitarios
    1.63
    蒟
    1.63
     kimdir
    1.62
    Activations Density 0.015%

    No Known Activations