© 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. 22-GEMMASCOPE-RES-131K
    7. 11072
    Prev
    Next
    INDEX
    Explanations

    country codes and names

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

    This neuron strongly activates on short subword tokens corresponding to language‐code identifiers (ISO 639 codes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     its
    -1.52
    nalité
    -1.39
    部に
    -1.24
    =?,
    -1.23
    なんですよ
    -1.22
    ₱
    -1.21
     cálculos
    -1.10
     gustar
    -1.09
    の地
    -1.09
    汛
    -1.09
    POSITIVE LOGITS
    どちらも
    1.22
    both
    1.16
    お
    1.07
    <bos>
    1.06
    と
    1.03
    がありますが
    1.01
     both
    1.00
     många
    0.99
    很多
    0.98
     sowohl
    0.98
    Activations Density 0.004%

    No Known Activations