© 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. 22-GEMMASCOPE-RES-131K
    7. 12882
    Prev
    Next
    INDEX
    Explanations

    starting points or initial actions

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

    This neuron detects sentence boundaries—strongly activating on sentence-initial words and ending punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Recently
    -1.53
    recently
    -1.41
     will
    -1.41
     Recently
    -1.38
     recently
    -1.32
     недавно
    -1.30
     récemment
    -1.29
    ！！！！！
    -1.26
    Yesterday
    -1.25
    ！！！！
    -1.23
    POSITIVE LOGITS
     initially
    2.17
     initial
    2.08
     immediately
    1.98
     anfangs
    1.87
     starting
    1.86
     zunächst
    1.80
     począ
    1.76
     started
    1.70
     eventually
    1.66
     сразу
    1.66
    Activations Density 0.077%

    No Known Activations