© 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. 66614
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or sequences

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

    The neuron responds to commas used as separators—especially those delimiting items in a list or sequence.

    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
    😖
    -1.22
    😵
    -1.19
    💞
    -1.16
    😩
    -1.14
    😘
    -1.13
    ♡♡
    -1.11
     idéia
    -1.11
     ♡
    -1.11
    😌
    -1.09
    😳
    -1.09
    POSITIVE LOGITS
    https
    1.16
     метал
    1.15
    <strong>
    1.05
    . 
    1.03
    めちゃくちゃ
    1.01
     covid
    1.00
    ​
    1.00
     COVID
    0.98
    icose
    0.98
    </strong>
    0.98
    Activations Density 0.052%

    No Known Activations