© 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. 120057
    Prev
    Next
    INDEX
    Explanations

    magna cum laude

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

    This neuron activates on the first significant word of a new block or heading (i.e. the very first content word in titles or section‐beginning lines).

    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
    抬手
    -1.70
     is
    -1.65
    lations
    -1.63
    ࿊
    -1.62
    衿
    -1.62
    鲩
    -1.57
    
    -1.53
     hago
    -1.52
     การ
    -1.52
     následu
    -1.51
    POSITIVE LOGITS
    5
    2.08
    利的
    1.61
    Both
    1.60
    卨
    1.58
     doté
    1.52
    淶
    1.47
    7
    1.47
     veta
    1.46
     Remember
    1.45
    𝓦
    1.41
    Activations Density 0.020%

    No Known Activations