© 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. 72393
    Prev
    Next
    INDEX
    Explanations

    code elements and punctuation

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

    This neuron detects programming identifiers (variable, parameter, and field names) in code snippets.

    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
    Ȝ
    -1.18
    ဒ
    -1.05
    プ
    -1.05
    /***
    -1.02
    ボール
    -1.02
    故事
    -1.02
    ケ
    -0.98
    پ
    -0.97
     bemerk
    -0.97
    分类
    -0.97
    POSITIVE LOGITS
     then
    1.37
    pantalones
    1.34
     now
    1.19
     this
    1.15
    alties
    1.13
    onekana
    1.12
     хочет
    1.07
     would
    1.06
     today
    1.05
     ministros
    1.05
    Activations Density 0.033%

    No Known Activations