© 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. 75634
    Prev
    Next
    INDEX
    Explanations

    AMC, Geek, Lenny, PDA, OTC, Weiner

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

    This neuron detects sequences of uppercase letters—acronyms or initialisms.

    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
    豨
    -2.72
     burbu
    -2.48
     車場
    -2.47
    4
    -2.36
     فانت
    -2.36
    珢
    -2.33
     anunciou
    -2.33
    vantaged
    -2.31
    个
    -2.30
     Aktivität
    -2.25
    POSITIVE LOGITS
    灃
    2.42
     &&
    2.27
    </strong>
    2.23
     worrying
    2.20
    偏偏
    2.13
     insanların
    2.00
     hikay
    2.00
     Whether
    2.00
     insanlar
    1.98
     процессов
    1.98
    Activations Density 0.007%

    No Known Activations