© 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. 71676
    Prev
    Next
    INDEX
    Explanations

    here in different languages

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

    The neuron strongly activates on mentions of websites, URLs, and related web‐address terms.

    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
    那边
    -0.98
     εκεί
    -0.90
     következő
    -0.81
    ⟩
    -0.80
     savez
    -0.80
    Huh
    -0.79
     ſuch
    -0.79
    Net
    -0.79
     lép
    -0.79
    说得
    -0.78
    POSITIVE LOGITS
     here
    3.80
     aquí
    2.22
     здесь
    2.11
    here
    2.02
    在这里
    1.94
    Here
    1.90
    這裡
    1.88
     сюда
    1.81
     Here
    1.80
    这里
    1.80
    Activations Density 0.058%

    No Known Activations