© 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. 34-GEMMASCOPE-RES-131K
    7. 103409
    Prev
    Next
    INDEX
    Explanations

    non-English words with punctuation

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

    This neuron fires strongly on quoted string literals in localization/resource definitions (e.g. translation entries).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     our
    -1.03
    .”
    -1.02
     انتظ
    -0.95
     unserer
    -0.94
     và
    -0.94
    ”.
    -0.92
    -“
    -0.92
    cityName
    -0.91
    에도
    -0.88
    ț
    -0.88
    POSITIVE LOGITS
     internes
    1.04
    biega
    1.00
     escalier
    0.98
     betreffende
    0.97
     royaume
    0.96
     verle
    0.94
     minimale
    0.93
     ACTS
    0.93
    ???:
    0.92
    Donnerstag
    0.91
    Activations Density 0.034%

    No Known Activations