© 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. 1524
    Prev
    Next
    INDEX
    Explanations

    special characters marking sections

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

    The neuron fires on lines made up of repeated punctuation characters (like “===”, “+++”, “----”, “***”, “~~~”) that serve as section headers or separators.

    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
     Bukan
    -1.62
     DOING
    -1.41
     serão
    -1.40
     NON
    -1.38
    Regressor
    -1.36
    argu
    -1.34
     ولكن
    -1.34
    since
    -1.34
    すみません
    -1.33
    返信
    -1.30
    POSITIVE LOGITS
    ↵
    1.49
     by
    1.43
     burgeoning
    1.30
     continúas
    1.27
    鷺
    1.23
    :
    1.22
     gave
    1.21
     hermosa
    1.20
     Females
    1.20
    ácií
    1.19
    Activations Density 0.086%

    No Known Activations