© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130065
    Prev
    Next
    INDEX
    Explanations

    This neuron detects two-letter lowercase alphabetic codes (e.g. ISO language/locale identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    language codes and names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     شوند
    -1.13
     DÍA
    -1.07
    にほんブログ村
    -1.07
     costuras
    -1.05
     people
    -1.02
     changes
    -1.00
    Ито
    -1.00
    见了
    -0.98
     INFORMACIÓN
    -0.96
     before
    -0.94
    POSITIVE LOGITS
     flamboyant
    1.30
     whimsical
    1.24
     delectable
    1.11
     exceptionally
    1.05
     decidedly
    1.05
    Литература
    1.04
    BUT
    1.03
     quintessential
    1.02
     principalmente
    1.01
     famed
    1.01
    Activations Density 0.001%

    No Known Activations