© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66944
    Prev
    Next
    INDEX
    Explanations

    cannot, negative, not

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

    The neuron consistently fires on tokens that mark negation or negative polarity (e.g. “impossible,” “negative,” verb suffixes meaning “cannot,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     not
    -1.72
    しておく
    -1.53
    ဴ
    -1.50
    厛
    -1.49
    Слайд
    -1.48
     concentra
    -1.48
    Пита
    -1.48
    Ваш
    -1.47
    Ꮞ
    -1.47
    Извест
    -1.46
    POSITIVE LOGITS
    мо
    1.59
    ка
    1.56
    2
    1.54
    歺
    1.47
    ‼️
    1.46
    ='"+
    1.38
    t
    1.38
    ви
    1.34
    ла
    1.34
    {
    1.33
    Activations Density 0.007%

    No Known Activations