© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106490
    Prev
    Next
    INDEX
    Explanations

    GPL software license identifier

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

    This neuron detects numeric literals (multi‐digit numbers) in code, such as version numbers, license identifiers, and other numeric constants.

    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
     Confe
    -0.86
     首页
    -0.82
    BackColor
    -0.81
     SCN
    -0.80
     zwarte
    -0.79
    Mania
    -0.79
     purpo
    -0.77
    ogues
    -0.77
    źródło
    -0.77
     教程
    -0.77
    POSITIVE LOGITS
    hilterra
    0.77
     modular
    0.77
    व
    0.77
    ligere
    0.74
     specifik
    0.73
     viewDidLoad
    0.73
    Selectors
    0.72
    rove
    0.70
     NFT
    0.70
    emi
    0.70
    Activations Density 0.003%

    No Known Activations