© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84481
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

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

    The neuron is looking for punctuation characters (especially quotation marks, periods, and commas) in code/JSON snippets.

    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
    濑
    -1.14
     al
    -1.10
    ne
    -1.07
     
    -1.07
    ('
    -1.05
     AL
    -1.05
    for
    -1.04
     con
    -1.04
     su
    -1.02
    d
    -1.00
    POSITIVE LOGITS
    今日も
    1.37
     vôtre
    1.35
    先週
    1.31
     veramente
    1.30
     nastro
    1.26
     comentários
    1.26
    前回の
    1.25
    Très
    1.23
    Интере
    1.21
     diing
    1.21
    Activations Density 0.031%

    No Known Activations