© 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. 34-GEMMASCOPE-RES-131K
    4. 116837
    Prev
    Next
    INDEX
    Explanations

    constructor import Autowired

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

    The neuron fires on numeric literals in code, detecting tokens that are numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    oredCriteria
    -0.81
    hasOwnProperty
    -0.81
    нение
    -0.79
     "),
    -0.79
     bersi
    -0.76
     предлага
    -0.75
    __[
    -0.75
     山田
    -0.74
     verliert
    -0.74
     entsteht
    -0.74
    POSITIVE LOGITS
     thank
    1.12
     thanks
    1.11
     Thank
    1.07
     thanking
    1.02
     Thanks
    1.02
     thanked
    0.98
    Thank
    0.97
     final
    0.94
     thankful
    0.93
    Thanks
    0.92
    Activations Density 0.008%

    No Known Activations