© 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. 34-GEMMASCOPE-RES-131K
    7. 6808
    Prev
    Next
    INDEX
    Explanations

    code brackets and symbols context

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

    The neuron fires most strongly on programming‐language comment delimiters (e.g. block comment closers like “*/”) and related comment‐block syntax.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    심
    -0.69
     Ren
    -0.68
    ชน
    -0.67
    держан
    -0.66
    Matrices
    -0.65
    Reno
    -0.65
     Chico
    -0.64
    балан
    -0.63
     进
    -0.63
     Dubai
    -0.63
    POSITIVE LOGITS
    directional
    0.76
    に登場
    0.73
    ᠵ
    0.67
     janela
    0.66
     zakup
    0.65
     authService
    0.65
    proc
    0.65
    owanej
    0.64
     analysis
    0.63
    setopt
    0.63
    Activations Density 0.071%

    No Known Activations