© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108523
    Prev
    Next
    INDEX
    Explanations

    starting sentences with quote marks

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

    The neuron detects the presence of direct speech or quoted passages, especially the opening quotation mark and the initial words of a quote.

    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
    сюда
    -1.24
     totalement
    -1.15
    ковые
    -1.09
     interessante
    -1.06
     complètement
    -1.04
    無駄
    -1.03
     kurzer
    -1.02
     relativement
    -1.02
    之色
    -0.99
     gefahren
    -0.99
    POSITIVE LOGITS
     when
    2.11
     if
    1.88
     there
    1.66
     even
    1.61
     it
    1.53
     now
    1.52
     people
    1.49
     before
    1.41
     during
    1.39
     initially
    1.38
    Activations Density 0.013%

    No Known Activations