© 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. 10-GEMMASCOPE-RES-131K
    7. 42930
    Prev
    Next
    INDEX
    Explanations

    seize illicit property

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

    The neuron detects words that convey “seizing” or taking hold of something—e.g. seize, seize on, initiative, advantage, opportunity, Carpe (as in “Carpe Diem”).

    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
    "-"
    -2.03
    ar
    -1.84
    zzzz
    -1.84
    d
    -1.77
     ghz
    -1.74
    "....
    -1.74
     Lijst
    -1.65
    -_-
    -1.65
    wwwwwwww
    -1.65
    😂😂😂😂
    -1.64
    POSITIVE LOGITS
    ghế
    1.83
     wodurch
    1.80
    ValueStyle
    1.70
    tisgarh
    1.63
     weshalb
    1.61
    ⵌ
    1.55
    隄
    1.53
    栝
    1.52
    ݇
    1.50
    ་་
    1.49
    Activations Density 0.009%

    No Known Activations