© 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. 22-GEMMASCOPE-RES-131K
    7. 71680
    Prev
    Next
    INDEX
    Explanations

    common programming suffixes and symbols

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

    This neuron responds to all-caps identifiers or acronyms (e.g. configuration constants, macro names, and other uppercase code tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    tiously
    -1.06
     During
    -1.05
     censiti
    -1.03
    に行ってきました
    -1.01
     hırka
    -1.00
    قلاب
    -0.95
    
    -0.93
    ֶ
    -0.91
     misused
    -0.91
    nsylvania
    -0.90
    POSITIVE LOGITS
     ™
    1.22
    などが
    1.19
    などを
    1.05
    zenden
    1.04
     startet
    1.04
     tog
    1.02
    coupled
    1.01
    <bos>
    1.01
     introducción
    0.99
     choses
    0.97
    Activations Density 0.080%

    No Known Activations