© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27996
    Prev
    Next
    INDEX
    Explanations

    quoted abbreviations and contractions

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

    The neuron is detecting occurrences of the typographic right single quotation mark (curly apostrophe).

    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
    というわけで
    -2.78
    嫫
    -2.73
    媖
    -2.70
    Going
    -2.56
    Before
    -2.50
     ostensibly
    -2.48
    どうやら
    -2.44
     untuk
    -2.42
    彣
    -2.42
     decreasing
    -2.41
    POSITIVE LOGITS
     we
    3.44
    [
    3.14
     quintessential
    2.92
    "
    2.63
     Dinas
    2.52
     flamboyant
    2.44
     monumental
    2.39
     nová
    2.28
     Then
    2.27
     relentless
    2.27
    Activations Density 0.002%

    No Known Activations