© 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. 22-GEMMASCOPE-RES-131K
    7. 84215
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

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

    The neuron fires on words that are part of spelled‐out multiword technical terms serving as expansions of acronyms (e.g. “Orthogonal Frequency Division Multiple Access,” “deoxyribonucleic acid,” “Vertical Cavity Surface Emitting Laser,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    madison
    -1.02
    感じで
    -0.98
    ところに
    -0.98
    所で
    -0.95
    gigabyte
    -0.94
    rabaya
    -0.93
     къде
    -0.92
     identified
    -0.91
     clearly
    -0.90
    クシー
    -0.90
    POSITIVE LOGITS
    )
    1.18
    }
    1.00
    توضیحات
    1.00
    Namun
    0.95
    ),
    0.90
     Lewes
    0.90
     azonban
    0.90
    但是在
    0.89
    ）
    0.88
    stances
    0.88
    Activations Density 0.107%

    No Known Activations