© 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. 10-GEMMASCOPE-RES-131K
    7. 80758
    Prev
    Next
    INDEX
    Explanations

    Sis, dl, SG abbreviation suffixes

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

    The neuron strongly activates on short, letter‐only tokens used as acronyms or abbreviations (e.g. “SIS” or “dl”).

    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
    0
    -4.03
    3
    -3.61
     \
    -3.30
    7
    -3.23
    2
    -3.13
    <b>
    -3.00
     Its
    -2.89
    <i>
    -2.89
    1
    -2.80
    5
    -2.72
    POSITIVE LOGITS
    😰
    3.02
     itſelf
    2.78
     吸
    2.73
    铼
    2.67
    😶
    2.67
    😵
    2.67
    🐈
    2.67
    🫠
    2.66
    🫣
    2.64
    🥹
    2.58
    Activations Density 0.003%

    No Known Activations