© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45167
    Prev
    Next
    INDEX
    Explanations

    Asian and OPEC"""

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

    The neuron is tuned to spot uppercase acronyms of international or regional organizations.

    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
    訁
    -2.25
    渽
    -2.23
     gritty
    -2.09
    嬲
    -2.08
     müsste
    -2.05
    '
    -1.97
    蜮
    -1.96
     overwhelming
    -1.94
    冉
    -1.94
     Два
    -1.93
    POSITIVE LOGITS
    E
    2.20
    但却
    1.99
    ments
    1.99
    镦
    1.99
     organismes
    1.99
    硨
    1.93
    悒
    1.92
    M
    1.91
    髣
    1.89
     pembe
    1.85
    Activations Density 0.005%

    No Known Activations