© 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. 73781
    Prev
    Next
    INDEX
    Explanations

    already + followed by verb

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

    The neuron strongly activates on the adverb “already” (and its forms in contractions).

    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
    ようですが
    -1.59
    𖥧
    -1.51
    みんなの
    -1.46
    乜
    -1.46
    こだ
    -1.46
    大家的
    -1.45
     poten
    -1.45
    ではでは
    -1.43
    も同じ
    -1.43
    ズキ
    -1.41
    POSITIVE LOGITS
    「
    1.79
    、
    1.77
    ،
    1.76
    包括
    1.66
    :
    1.58
    ，
    1.57
    像
    1.54
    са
    1.45
    т
    1.45
    The
    1.43
    Activations Density 0.007%

    No Known Activations