© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15553
    Prev
    Next
    INDEX
    Explanations

    old followed by words

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

    The neuron specifically activates on occurrences of the word “old.”

    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
    Negative Logits
    很喜欢
    -1.54
     April
    -1.23
     очень
    -1.20
     själva
    -1.18
     värld
    -1.17
    崛
    -1.16
     folgende
    -1.16
     прибли
    -1.14
    変わった
    -1.14
     Eight
    -1.13
    POSITIVE LOGITS
     ダンス
    1.27
     who
    1.21
     continually
    1.21
     milyen
    1.17
     poesia
    1.13
    ل
    1.12
     carcasa
    1.12
     conversación
    1.11
     Privacidade
    1.09
     we
    1.08
    Activations Density 0.021%

    No Known Activations