© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112996
    Prev
    Next
    INDEX
    Explanations

    technical pattern definitions

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

    the word "pattern" (or "Pattern") in programming and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the word “pattern” (in code or configuration contexts).

    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
    </strong>
    -2.38
    AddHtmlAttribute
    -2.30
    。"
    -2.13
     スクール
    -2.08
    纽约
    -2.08
     ウォッチ
    -2.00
     conocidas
    -1.94
    嗥
    -1.93
    ！"
    -1.91
    ﻒ
    -1.91
    POSITIVE LOGITS
    .
    2.91
     Thus
    2.17
    What
    2.09
    Thus
    2.09
     Therefore
    2.05
    Always
    2.05
    Actually
    2.02
    するので
    1.99
     Accordingly
    1.95
    Compared
    1.94
    Activations Density 0.013%

    No Known Activations