© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47040
    Prev
    Next
    INDEX
    Explanations

    continue to [verb]

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

    The neuron specifically detects the English word “to,” as commonly used (for example, in infinitive constructions).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     شروع
    -1.73
     mulai
    -1.66
     commencent
    -1.65
     zač
    -1.58
    开始
    -1.57
     beginnen
    -1.55
     начина
    -1.49
     commencer
    -1.45
     começar
    -1.45
     beginning
    -1.40
    POSITIVE LOGITS
     be
    1.61
    B
    1.27
    m
    1.23
     amazed
    1.16
    M
    1.16
    L
    1.15
    r
    1.14
    R
    1.12
     hold
    1.11
    S
    1.09
    Activations Density 0.014%

    No Known Activations