© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124666
    Prev
    Next
    INDEX
    Explanations

    he followed by verbs

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

    The neuron is primarily triggered by past‐tense verbs describing actions (e.g. wrote, recorded, co‐founded, produced, held, left).

    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
     każdego
    -1.43
    岀
    -1.38
     Brunnen
    -1.37
     Deixe
    -1.35
     توانند
    -1.34
    描く
    -1.34
    genheiten
    -1.33
     jednego
    -1.27
    רְ
    -1.26
     aliviar
    -1.26
    POSITIVE LOGITS
     on
    1.59
     and
    1.57
     own
    1.46
     with
    1.46
     البته
    1.40
    \
    1.38
     the
    1.37
     трех
    1.26
     vermel
    1.25
     for
    1.24
    Activations Density 0.037%

    No Known Activations