© 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. 71961
    Prev
    Next
    INDEX
    Explanations

    NC abbreviation

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

    The neuron fires on the exact token “NC,” marking occurrences of that two‐letter uppercase code.

    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
     They
    -2.42
     Also
    -2.39
     So
    -2.31
     Notably
    -2.22
    IVERS
    -2.17
    樣的
    -2.16
     Seem
    -2.16
    鈇
    -2.13
    (
    -2.13
    "
    -2.09
    POSITIVE LOGITS
    ました
    2.48
     evade
    2.25
     detención
    2.22
     alters
    2.20
    髡
    2.14
    s
    2.13
     destrucción
    2.09
     asamblea
    2.08
    矗
    2.08
    袂
    2.06
    Activations Density 0.003%

    No Known Activations