© 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. 11694
    Prev
    Next
    INDEX
    Explanations

    looking ahead, predictive, esthetic, Wang Zongdi

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

    The neuron fires on occurrences of the word “ahead.”

    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
    ſelves
    -1.38
     posta
    -1.37
     ..............
    -1.35
     preoc
    -1.34
     novi
    -1.33
    TacToe
    -1.32
    ;?
    -1.31
    恪
    -1.30
    }),
    -1.30
    っている
    -1.28
    POSITIVE LOGITS
     fuertemente
    1.60
     supuestamente
    1.59
    1.57
     thingy
    1.50
     wyboru
    1.49
     incessantly
    1.48
    薷
    1.46
     locaux
    1.38
     constantemente
    1.38
    niosek
    1.37
    Activations Density 0.004%
    No Known Activations