© 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. 13954
    Prev
    Next
    INDEX
    Explanations

    cause and effect

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

    The neuron detects strong causative verbs (e.g., “cause,” “caused,” “induce”) that express a cause‐and‐effect relation.

    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
    姈
    -2.22
    횃
    -2.20
    橚
    -1.95
     procedimiento
    -1.76
     ۱۴
    -1.72
    ቬ
    -1.72
     Sábado
    -1.71
    又是一
    -1.71
     ۷
    -1.70
    但却
    -1.70
    POSITIVE LOGITS
     in
    2.08
     Here
    1.69
    >
    1.62
     廠
    1.62
     Perhaps
    1.51
     Certainly
    1.47
     Roughly
    1.38
    釩
    1.37
     uproar
    1.37
     Several
    1.34
    Activations Density 0.105%

    No Known Activations