© 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. 59185
    Prev
    Next
    INDEX
    Explanations

    international country codes/abbreviations

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

    The neuron is triggered by all‐caps abbreviations or acronyms (short uppercase tokens).

    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
    Pesquisa
    -1.28
    besos
    -1.27
    ्ञ
    -1.20
     another
    -1.19
     tumbuhan
    -1.18
     Autorin
    -1.16
    Fornecedor
    -1.16
     only
    -1.15
    uyasha
    -1.14
     LIVER
    -1.13
    POSITIVE LOGITS
     was
    1.39
    鼉
    1.32
     to
    1.21
     into
    1.21
    ingular
    1.19
    wiegend
    1.18
    さっそく
    1.18
    他知道
    1.13
    AppRoutingModule
    1.12
     några
    1.11
    Activations Density 0.491%

    No Known Activations