© 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. 22-GEMMASCOPE-RES-131K
    7. 26397
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    The neuron activates on numeric literals (both integers and decimals) 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
    inaug
    -1.01
     frecuentemente
    -0.96
     altamente
    -0.96
     שלא
    -0.94
     stratég
    -0.93
     первых
    -0.93
     rése
    -0.91
    SUBJECT
    -0.91
     FRE
    -0.90
     kül
    -0.90
    POSITIVE LOGITS
     now
    1.02
    ล่า
    1.00
    では
    0.94
    Now
    0.83
    最新
    0.82
    mutex
    0.81
    ']
    0.81
     it
    0.79
     ネット
    0.79
    ↵↵
    0.78
    Activations Density 0.003%

    No Known Activations