© 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. 10-GEMMASCOPE-RES-131K
    4. 110999
    Prev
    Next
    INDEX
    Explanations

    explains "in it" descriptions

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

    The neuron fires on the two-word sequence “in it.”

    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
    W
    -2.22
    ürnberg
    -2.17
    	
    -2.14
    R
    -2.08
    Ⲉ
    -2.02
    Where
    -1.96
    ‌ها
    -1.96
    to
    -1.92
    Let
    -1.91
    Are
    -1.91
    POSITIVE LOGITS
    izoen
    1.97
    lijke
    1.88
    
    1.85
    
    1.82
     siquiera
    1.80
    
    1.75
    llavero
    1.74
    潆
    1.73
     aqueles
    1.69
     мнение
    1.69
    Activations Density 0.012%

    No Known Activations