© 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. 105280
    Prev
    Next
    INDEX
    Explanations

    words beginning with pres

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

    This neuron detects the character sequence “pres” when it appears as a token or token prefix (e.g., in “presynaptic” or “presentable”).

    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
     
    -4.56
    ing
    -4.09
    2
    -3.94
    1
    -3.92
    3
    -3.84
    5
    -3.67
    8
    -3.55
    7
    -3.52
    4
    -3.47
    a
    -2.95
    POSITIVE LOGITS
    嗵
    3.23
    嫘
    3.08
    闼
    3.05
     汽车
    3.03
    鶿
    2.98
    鴆
    2.86
     extré
    2.84
    膛
    2.83
     市场
    2.80
    榈
    2.80
    Activations Density 0.008%

    No Known Activations