© 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. 75398
    Prev
    Next
    INDEX
    Explanations

    list elements and variable names

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

    The neuron responds to numeric tokens (literal numbers, offsets or sizes) in code.

    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
     or
    -1.98
     While
    -1.59
     while
    -1.59
    While
    -1.48
     intricacies
    -1.38
    Other
    -1.36
     I
    -1.33
     continual
    -1.29
     encourage
    -1.27
     increase
    -1.27
    POSITIVE LOGITS
    鐽
    1.50
     auffi
    1.50
    也是
    1.49
    킁
    1.46
     alfo
    1.45
     utilisé
    1.44
     alpes
    1.40
    癭
    1.40
     BIBLIO
    1.38
     plafon
    1.38
    Activations Density 0.028%

    No Known Activations