© 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. 69157
    Prev
    Next
    INDEX
    Explanations

    technical acronyms and abbreviations

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

    The neuron specializes in spotting technical measurement terms—especially pressure-related quantities and their abbreviations (e.g. “contact pressure,” “ACP,” “MAP,” “MIPS,” “MEPS”).

    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
     who
    -1.61
     renkli
    -1.48
     bailarina
    -1.41
     решили
    -1.37
    ᠂
    -1.32
     conster
    -1.30
     disparition
    -1.30
     reves
    -1.30
     pronounced
    -1.28
     miſ
    -1.28
    POSITIVE LOGITS
     you
    2.05
     Sometimes
    1.35
     rate
    1.30
     Also
    1.27
     between
    1.27
     on
    1.24
     zowel
    1.22
     tidligere
    1.20
     entweder
    1.20
     also
    1.18
    Activations Density 0.507%

    No Known Activations