© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1864
    Prev
    Next
    INDEX
    Explanations

    time sequencing

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

    The neuron activates strongly on numeric tokens (years, page numbers, IDs, and other numbers).

    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
     especially
    -1.54
     sometimes
    -1.34
     particularly
    -1.30
     иногда
    -1.18
     for
    -1.09
    например
    -1.04
     beispielsweise
    -1.04
    когда
    -1.02
     indeed
    -1.02
     например
    -1.02
    POSITIVE LOGITS
     then
    2.98
     subsequent
    2.95
     subsequently
    2.81
     later
    2.70
     shortly
    2.66
     Subsequently
    2.53
     that
    2.50
     thereafter
    2.42
    翌
    2.34
    その後
    2.31
    Activations Density 0.145%

    No Known Activations