© 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. 10-GEMMASCOPE-RES-131K
    7. 85150
    Prev
    Next
    INDEX
    Explanations

    words starting with nor

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

    The neuron is highly selective for the exact token “Nor” (appearing as a standalone or prefix in proper names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    渽
    -3.58
    vège
    -3.52
     lidé
    -3.38
     nových
    -3.14
     lidí
    -3.11
    簠
    -3.11
    骘
    -3.08
     próximas
    -3.06
     ochran
    -3.03
    뿅
    -2.98
    POSITIVE LOGITS
    It
    4.56
    2
    4.44
    9
    4.28
    3
    4.13
    1
    4.13
    8
    3.91
    "
    3.80
    The
    3.75
    5
    3.70
    6
    3.53
    Activations Density 0.009%

    No Known Activations