© 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. 34-GEMMASCOPE-RES-131K
    7. 64824
    Prev
    Next
    INDEX
    Explanations

    translation services and localization

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

    This neuron detects markup syntax elements—especially XML/HTML tags and their attribute names (e.g. the “<” token, “translation,” “id,” “lang,” “version,” etc.).

    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
     alti
    -0.76
     conjugate
    -0.73
     Mundi
    -0.73
     DED
    -0.73
    Pob
    -0.73
    mg
    -0.72
     seoul
    -0.72
     Oce
    -0.71
    もしろ
    -0.71
     hoc
    -0.69
    POSITIVE LOGITS
     sko
    1.04
     equivalence
    1.01
     faithfulness
    0.91
    sko
    0.89
     norms
    0.81
     odbior
    0.80
     marki
    0.80
     TT
    0.80
    糬
    0.79
     Tiere
    0.78
    Activations Density 0.019%

    No Known Activations