© 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. 10-GEMMASCOPE-RES-131K
    7. 41442
    Prev
    Next
    INDEX
    Explanations

    attributing or ascribing to

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

    This neuron detects instances of attribution verbs that assign causality, intention, or qualities (e.g., "attribute," "ascribe," "attributing").

    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
     или
    -2.48
    ()
    -2.19
    鷙
    -2.16
    This
    -2.06
     нее
    -2.05
     atau
    -1.99
    ઁ
    -1.99
    鯪
    -1.97
    It
    -1.93
    ."
    -1.88
    POSITIVE LOGITS
     
    2.83
    ↵
    2.31
     verminder
    2.09
    鈈
    2.03
     небольшие
    1.95
    なんですが
    1.89
     имеются
    1.85
    Helps
    1.81
     casado
    1.77
    未必
    1.76
    Activations Density 0.013%

    No Known Activations