© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8468
    Prev
    Next
    INDEX
    Explanations

    arguing for or against

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

    The neuron detects tokens that are inflections of the verb “argue,” marking when a text presents or states an argument.

    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
    ]
    -3.59
    Ꮞ
    -2.89
    ༛
    -2.59
    趼
    -2.53
    ’
    -2.52
    喈
    -2.47
     '
    -2.41
     écrit
    -2.39
    剮
    -2.39
    姈
    -2.34
    POSITIVE LOGITS
     bestellt
    2.86
    屺
    2.81
     gekauft
    2.69
     aktiviert
    2.67
    妧
    2.66
    呓
    2.63
     sanitarios
    2.52
    茑
    2.52
    紕
    2.50
    涐
    2.47
    Activations Density 0.005%

    No Known Activations