© 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. 10-GEMMASCOPE-RES-131K
    7. 8684
    Prev
    Next
    INDEX
    Explanations

    programming timestamps and jargon

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

    The neuron fires strongly on the literal “['” token—that is, it picks up opening square brackets used to introduce bracketed references, labels, or section headings.

    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
    _
    -2.00
     Octobre
    -1.78
     København
    -1.66
     februari
    -1.60
     Septembre
    -1.52
    ud
    -1.52
    
    -1.48
     onsdag
    -1.47
     textil
    -1.47
     januari
    -1.47
    POSITIVE LOGITS
     produttore
    1.57
     incluindo
    1.53
     stehenden
    1.50
    不过是
    1.47
     and
    1.45
     sorprender
    1.44
    malıdır
    1.41
    unikasi
    1.39
    ↵↵
    1.38
    fantasia
    1.37
    Activations Density 0.005%

    No Known Activations