© 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. 34-GEMMASCOPE-RES-131K
    4. 66329
    Prev
    Next
    INDEX
    Explanations

    words after "Sun"

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

    This neuron detects SQL UPDATE statements (e.g. the keywords UPDATE, SET, WHERE and table/column identifiers connected by underscores).

    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
    Magick
    -0.76
     temperatuur
    -0.71
     gevonden
    -0.70
    magic
    -0.69
    வத
    -0.69
    stown
    -0.69
     хол
    -0.68
    шна
    -0.68
    皎
    -0.68
     las
    -0.67
    POSITIVE LOGITS
     talent
    1.06
     talents
    1.00
     Talent
    0.79
     binocular
    0.78
    talent
    0.77
     hotfix
    0.76
    RIO
    0.75
    焼き
    0.74
     Vodka
    0.71
     operands
    0.69
    Activations Density 0.058%

    No Known Activations