© 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. 113884
    Prev
    Next
    INDEX
    Explanations

    it's no

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

    The neuron specifically activates on the standalone negative token “no.”

    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
    玙
    -1.48
     appea
    -1.43
    ſſen
    -1.40
    詎
    -1.38
    atly
    -1.34
    좆
    -1.32
     grosir
    -1.30
    お
    -1.29
    interesting
    -1.29
    arture
    -1.29
    POSITIVE LOGITS
    其余
    1.50
     pierna
    1.39
    fony
    1.38
    ங
    1.35
     their
    1.35
     they
    1.30
    acija
    1.30
    になれば
    1.30
    でしたか
    1.28
    別れ
    1.28
    Activations Density 0.004%

    No Known Activations