© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70504
    Prev
    Next
    INDEX
    Explanations

    not having or being

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

    This neuron detects negated states of having or being able—especially phrases like “not having” or “not being able to.”

    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
    寕
    -2.17
     touted
    -2.03
    滙
    -1.92
     There
    -1.89
     our
    -1.89
    emplares
    -1.86
     中式
    -1.84
     tende
    -1.84
     увидел
    -1.83
    鄚
    -1.82
    POSITIVE LOGITS
    ():
    1.77
     necessarily
    1.68
    ating
    1.55
    ↵
    1.52
    啻
    1.52
    »,
    1.50
    ла
    1.45
    眉毛
    1.45
    ToRemove
    1.45
     especialidad
    1.45
    Activations Density 0.019%

    No Known Activations