© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9205
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

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

    The neuron detects long runs of consecutive slash characters (comment divider lines made of “/”).

    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
     แต่
    -3.22
     largas
    -2.31
    aktifkan
    -2.30
    時間
    -2.23
     But
    -2.20
     maravillosas
    -2.19
     OGSÅ
    -2.16
    !"
    -2.14
     但
    -2.09
     любит
    -2.09
    POSITIVE LOGITS
     unangemessene
    2.77
     vorigen
    2.59
     bestehende
    2.58
     zentrale
    2.56
     wichtige
    2.55
     genaue
    2.52
     klassische
    2.52
    </h3>
    2.50
    ity
    2.42
     offizielle
    2.41
    Activations Density 0.010%

    No Known Activations