© 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. 22-GEMMASCOPE-RES-131K
    7. 129692
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on timestamp-like numeric patterns (e.g. “HH:MM”) in diff or log entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    timestamps and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    sp
    -1.09
    OVE
    -0.94
    could
    -0.93
    th
    -0.91
    ’
    -0.90
     pubblica
    -0.89
     listed
    -0.88
    topia
    -0.88
     largely
    -0.88
    white
    -0.88
    POSITIVE LOGITS
    ésultat
    1.04
     elaborado
    1.03
     sentada
    1.00
     autre
    0.98
    Nuorodos
    0.96
    IARC
    0.96
     renfer
    0.95
     Weaving
    0.93
     Ради
    0.92
     concentrado
    0.92
    Activations Density 0.001%

    No Known Activations