© 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. 61135
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and questions

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

    The neuron fires on technical identifiers and component names (e.g. library/module names, protocol acronyms, and similar uppercase or underscore-delimited 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_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
    GRAFIA
    -1.66
    ны
    -1.52
     receber
    -1.39
     neun
    -1.38
    aney
    -1.37
     we
    -1.35
     begren
    -1.34
     alguns
    -1.33
    really
    -1.32
     "-
    -1.31
    POSITIVE LOGITS
    Вопрос
    1.44
    Oltre
    1.34
     this
    1.32
    Aujourd
    1.27
     September
    1.26
    Сайт
    1.26
     办
    1.25
    UILabel
    1.23
    Choisissez
    1.22
    ponenten
    1.21
    Activations Density 0.015%

    No Known Activations