© 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. 34-GEMMASCOPE-RES-131K
    7. 90625
    Prev
    Next
    INDEX
    Explanations

    terms starting with ND

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

    The neuron fires whenever it sees the two-letter token “nd” (in any casing), e.g. as part of abbreviations like ND.

    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
    anyeol
    -0.80
    enang
    -0.79
     进
    -0.79
     رائعة
    -0.79
     može
    -0.78
     failing
    -0.76
     Vö
    -0.75
     совершен
    -0.75
    iap
    -0.75
     專
    -0.75
    POSITIVE LOGITS
     ND
    1.30
    ND
    1.24
     nd
    1.22
     Nd
    1.05
     NDR
    1.01
    urance
    0.85
    coded
    0.85
    Nd
    0.80
    ternal
    0.80
    )”.
    0.79
    Activations Density 0.008%

    No Known Activations