© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99929
    Prev
    Next
    INDEX
    Explanations

    new

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

    The neuron fires on occurrences of “new” (and its equivalents like “nuevo,” “nueva,” “новый,” “uusi,” etc.) in various languages.

    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
    ↵↵
    -2.64
    ’
    -2.44
     wichtigste
    -2.42
    罴
    -2.42
     thre
    -2.41
    {
    -2.41
     viviendo
    -2.36
    ',
    -2.30
     gleiche
    -2.28
    -
    -2.25
    POSITIVE LOGITS
    躥
    3.34
    慜
    3.09
    新的
    2.80
     Previously
    2.72
     poesia
    2.61
     fashioned
    2.56
    簟
    2.56
     تستخدم
    2.53
    椟
    2.52
    на
    2.50
    Activations Density 0.003%

    No Known Activations