© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1373
    Prev
    Next
    INDEX
    Explanations

    class members, methods, and variables

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

    The neuron is picking out numeric literals (individual digits or multi‐digit numbers) in code and text.

    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
     empower
    -0.73
    labelledby
    -0.72
    КТ
    -0.68
    UTR
    -0.68
    ActionEvent
    -0.68
     taken
    -0.66
     ति
    -0.66
    +```
    -0.66
     capt
    -0.65
    aryngeal
    -0.65
    POSITIVE LOGITS
     variables
    1.55
     functions
    1.52
    变量
    1.38
     function
    1.35
    variables
    1.30
     static
    1.30
     constants
    1.21
    static
    1.20
     methods
    1.20
    functions
    1.20
    Activations Density 0.100%

    No Known Activations