© 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. 77364
    Prev
    Next
    INDEX
    Explanations

    ITU standardization recommendations

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

    The neuron strongly activates on mentions of technical or standards‐related contexts—especially organization names, engineering or telecommunications terms, and formal domain vocabulary.

    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
    atomic
    -0.79
    Third
    -0.77
    раздо
    -0.74
    alus
    -0.69
    Trans
    -0.69
     舞
    -0.66
    kologie
    -0.66
    ุด
    -0.66
    卫生间
    -0.66
    ֵ
    -0.66
    POSITIVE LOGITS
     ITU
    1.38
    ITU
    0.84
     Geneva
    0.79
     arrears
    0.78
     Recommendation
    0.77
     standardization
    0.77
    Itu
    0.77
     soportar
    0.76
     itu
    0.75
    rains
    0.74
    Activations Density 0.010%

    No Known Activations