© 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. 34-GEMMASCOPE-RES-131K
    7. 25807
    Prev
    Next
    INDEX
    Explanations

    date formats or numbers

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

    This neuron fires on vocabulary that lays out the sequence and timing of events in a football match commentary.

    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
     考
    -0.78
    zungs
    -0.71
    msgSender
    -0.71
     fieldNum
    -0.70
    usta
    -0.70
    गी
    -0.69
     MBS
    -0.68
     solidity
    -0.66
    therlands
    -0.65
    TopLeft
    -0.65
    POSITIVE LOGITS
     intestinal
    0.89
    intestinal
    0.88
    haling
    0.84
     Lampung
    0.76
    stamp
    0.75
    thaler
    0.74
     saltwater
    0.73
    勲
    0.73
    örg
    0.69
    índ
    0.69
    Activations Density 0.025%

    No Known Activations