© 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. 2225
    Prev
    Next
    INDEX
    Explanations

    staying up or awake

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

    The neuron fires strongly on tokens that represent quantitative information—numbers, measurements, counts, dosages, durations, or other numeric metrics.

    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
     daily
    -0.79
    orable
    -0.76
    daily
    -0.74
    PKCS
    -0.73
    덩
    -0.70
    quois
    -0.70
     Lungen
    -0.69
     cooldown
    -0.68
    äiv
    -0.68
    archived
    -0.68
    POSITIVE LOGITS
     awake
    3.25
     Awake
    2.41
    awake
    2.28
    Awake
    2.09
     wake
    2.08
     Wake
    1.80
     sleepless
    1.73
    Wake
    1.64
     insomnia
    1.62
    wake
    1.58
    Activations Density 0.030%

    No Known Activations