© 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. 34-GEMMASCOPE-RES-131K
    7. 102502
    Prev
    Next
    INDEX
    Explanations

    spatial relationships and sequence

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

    The neuron strongly responds to end‐of‐sentence periods, effectively spotting sentence boundaries marked by “.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     however
    -1.30
     therefore
    -1.16
    Therefore
    -1.10
     daher
    -1.05
     Therefore
    -1.04
     that
    -1.02
    however
    -1.01
     debido
    -0.97
     quindi
    -0.95
     original
    -0.94
    POSITIVE LOGITS
     behind
    1.59
     beside
    1.40
     beneath
    1.36
     across
    1.36
     Then
    1.31
     outside
    1.30
     then
    1.29
    Nearby
    1.27
     nearby
    1.17
     แล้ว
    1.16
    Activations Density 0.033%

    No Known Activations