© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74598
    Prev
    Next
    INDEX
    Explanations

    continually + gerunds/verbs

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

    The neuron specializes in spotting the adverb “continually.”

    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
    ↵↵
    -2.97
    𖣔
    -2.38
    i
    -2.28
     внеш
    -2.23
    𓇼
    -2.16
     уника
    -2.13
    เริ่ม
    -2.11
     Erhöhung
    -2.09
    怂
    -2.06
    仨
    -2.02
    POSITIVE LOGITS
    :^{
    2.91
    鹇
    2.88
    ╽
    2.61
    k
    2.44
    遄
    2.44
     these
    2.41
    ?"
    2.31
    蓥
    2.28
    ꕀ
    2.27
    䊏
    2.25
    Activations Density 0.001%

    No Known Activations