© 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. 22-GEMMASCOPE-RES-131K
    7. 128635
    Prev
    Next
    INDEX
    Explanations

    The neuron detects any token containing the substring “nick” (e.g. nick, nickel, Nickelodeon, nicknames).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    nick names and nickels

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    *
    -2.73
    I
    -2.56
    (
    -2.50
    時間
    -2.47
     belangrij
    -2.41
     necessario
    -2.41
     necessaria
    -2.36
    儈
    -2.33
    ↵↵
    -2.33
    on
    -2.28
    POSITIVE LOGITS
    鵙
    2.89
     voor
    2.55
     gustos
    2.45
    чем
    2.42
     ``
    2.34
    ſſen
    2.25
     ilg
    2.25
    IFYING
    2.23
     siquiera
    2.20
    鮠
    2.20
    Activations Density 0.021%

    No Known Activations