© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72599
    Prev
    Next
    INDEX
    Explanations

    C++ code following opening brace or parenthesis

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

    The neuron activates on numeric literals (integer or floating‐point constants) 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
     three
    -2.22
     five
    -2.22
     eight
    -2.09
     unrelenting
    -2.09
     two
    -2.08
     multifaceted
    -2.08
     before
    -2.06
     plethora
    -2.05
     Before
    -2.03
     sizeable
    -2.02
    POSITIVE LOGITS
    亹
    2.20
     peuvent
    2.20
    苼
    2.13
    秶
    2.00
     dando
    1.99
    螃
    1.98
     INTERNATIONAL
    1.98
     REALLY
    1.95
    llavero
    1.92
    
    1.91
    Activations Density 0.012%

    No Known Activations