© 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. 102930
    Prev
    Next
    INDEX
    Explanations

    paradox and irony

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

    The neuron fires on single, attention-grabbing topic or genre labels (e.g. “Paradox,” “Clickbait,” “Sarcasm,” “Loophole”) that typically appear as boldfaced or headline words.

    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
    ៥
    -0.93
    GARET
    -0.89
    roben
    -0.87
     influential
    -0.86
    劫
    -0.85
    beforeAll
    -0.84
     oat
    -0.84
    Profiles
    -0.83
     metaphor
    -0.82
    gives
    -0.82
    POSITIVE LOGITS
     about
    1.30
     regarding
    1.12
     galore
    1.02
     ridden
    1.00
    ridden
    0.99
     involving
    0.95
    laden
    0.92
     perpetrated
    0.91
     detector
    0.90
     acerca
    0.89
    Activations Density 0.069%

    No Known Activations