© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 18967
    Prev
    Next
    INDEX
    Explanations

    code with variable declarations

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

    The neuron fires on numeric literals in code (e.g. the numbers in parameter lists, macro definitions, etc.).

    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
     inond
    -1.70
     内衣
    -1.45
    öffnung
    -1.41
     dégâts
    -1.41
    🫅
    -1.40
    fanart
    -1.38
     coloriage
    -1.38
    跄
    -1.38
    értel
    -1.38
     célè
    -1.38
    POSITIVE LOGITS
    _
    1.94
    </h3>
    1.73
    f
    1.68
    3
    1.65
    il
    1.59
    </i>
    1.58
    č
    1.52
    v
    1.48
    <h3>
    1.48
     possibly
    1.47
    Activations Density 0.024%

    No Known Activations