© 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. 10-GEMMASCOPE-RES-131K
    7. 1638
    Prev
    Next
    INDEX
    Explanations

    sentence starts

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

    The neuron strongly activates on punctuation marks—especially commas and periods—that signal sentence boundaries.

    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
     The
    -1.95
     our
    -1.84
     to
    -1.82
     There
    -1.70
     has
    -1.69
     is
    -1.63
     In
    -1.63
     At
    -1.61
     Here
    -1.59
     And
    -1.55
    POSITIVE LOGITS
    selben
    2.45
     стоковые
    1.85
    殽
    1.80
    ⾝
    1.79
     baumwolle
    1.78
     стоковая
    1.74
     chilen
    1.73
     LIVING
    1.73
     abstrak
    1.72
    moderne
    1.70
    Activations Density 0.024%

    No Known Activations