© 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. 34-GEMMASCOPE-RES-131K
    7. 86788
    Prev
    Next
    INDEX
    Explanations

    negation with 'particular', 'special', or 'specific' context

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

    The neuron is a negation detector—it fires strongly on negative words like “not” (and its Russian equivalent “не”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    -1.16
     län
    -0.94
     tatuaje
    -0.93
     kade
    -0.91
     ſou
    -0.91
    ไม่
    -0.91
     fré
    -0.90
     akrab
    -0.89
    Modifier
    -0.88
     não
    -0.88
    POSITIVE LOGITS
     particularmente
    1.23
     speziell
    0.93
     particularly
    0.93
     específicamente
    0.88
     besonders
    0.88
     secret
    0.87
     Besonders
    0.87
     duża
    0.87
     lumen
    0.84
     obfusc
    0.84
    Activations Density 0.013%

    No Known Activations