© 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. 33204
    Prev
    Next
    INDEX
    Explanations

    no injuries or casualties

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

    The neuron fires on negation words (e.g. “no,” “not”).

    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
     sommeil
    -0.94
     sometimes
    -0.88
     bahkan
    -0.87
     участь
    -0.83
     évêque
    -0.81
    ị
    -0.81
     expérience
    -0.81
     Akad
    -0.81
     even
    -0.80
     Heft
    -0.80
    POSITIVE LOGITS
     immediately
    1.50
     immediate
    1.41
    immediately
    1.38
    Immediately
    1.21
    Immediate
    1.21
     Immediate
    1.20
     release
    1.20
     Immediately
    1.16
    immediate
    1.15
     motive
    1.12
    Activations Density 0.024%

    No Known Activations