© 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. 104230
    Prev
    Next
    INDEX
    Explanations

    programming code and functions

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

    The neuron is primarily detecting numeric tokens (integer literals or digits) 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_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
     haji
    -1.27
    Ār
    -1.22
    УДК
    -1.16
     enfans
    -1.15
     laku
    -1.14
     SITUATION
    -1.13
     Ayam
    -1.10
     сочи
    -1.09
     newOwner
    -1.09
     kuno
    -1.09
    POSITIVE LOGITS
     []:
    1.14
    ому
    1.09
     According
    1.09
    athi
    1.06
     detalló
    1.04
    odule
    1.03
    ђе
    1.00
    INAL
    1.00
    VStack
    1.00
     Сла
    0.99
    Activations Density 0.006%

    No Known Activations