© 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. 22-GEMMASCOPE-RES-131K
    7. 98338
    Prev
    Next
    INDEX
    Explanations

    SMTP server operations

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

    The neuron is a detector for the “<” token—i.e. angle-bracket syntax used in XML doc comments (e.g. <summary>) and in generic/type-parameter declarations.

    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
    EARCH
    -1.13
    zió
    -1.06
     WaitForSeconds
    -1.03
    了一会儿
    -1.03
    isième
    -1.03
    տ
    -1.00
    ૨
    -0.99
     contains
    -0.98
     *}$
    -0.97
    енты
    -0.97
    POSITIVE LOGITS
    Dill
    0.95
    ↵↵
    0.88
     hood
    0.80
     â
    0.79
    Nearby
    0.77
    <bos>
    0.77
     what
    0.76
     gimnasio
    0.75
    萦
    0.74
     deportivas
    0.73
    Activations Density 0.002%

    No Known Activations