© 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. 13358
    Prev
    Next
    INDEX
    Explanations

    programming keywords

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

    The neuron fires on isolated technical identifiers and keywords (e.g. API‐doc terms, class/field names, language keywords) in documentation.

    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
     xxii
    -1.14
     muualla
    -1.09
    就不会
    -1.06
     defire
    -1.02
    ’
    -1.00
    ly
    -0.98
    лись
    -0.97
     $(-
    -0.97
     zufolge
    -0.97
     lefs
    -0.96
    POSITIVE LOGITS
    nibus
    1.13
    LEIA
    1.11
     völlig
    1.11
     וּ
    1.08
     розо
    1.07
     abar
    1.06
    фин
    1.04
    तो
    1.02
    そのような
    1.01
    pergillus
    1.00
    Activations Density 0.000%

    No Known Activations