© 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. 69302
    Prev
    Next
    INDEX
    Explanations

    request data, headers, or errors

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

    The neuron activates on programming‐style identifiers—especially uppercase or CamelCase tokens like constants, type names, and macro names.

    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
    2
    -2.61
    {
    -2.53
    7
    -2.39
    4
    -2.33
    6
    -2.23
    [
    -2.17
    5
    -2.09
    s
    -2.08
    ]
    -2.03
    <
    -1.91
    POSITIVE LOGITS
     that
    1.88
     内装
    1.87
    罽
    1.80
    のイメージ
    1.79
     suche
    1.74
     gevaar
    1.72
    严肃
    1.71
    佉
    1.70
    
    1.70
    ならでは
    1.70
    Activations Density 0.009%

    No Known Activations