© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113510
    Prev
    Next
    INDEX
    Explanations

    timestamps and dates

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

    The neuron activates on occurrences of “timestamp” (and its plural “timestamps”) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    蓠
    -1.95
    其他
    -1.94
     \
    -1.86
     beberapa
    -1.80
    ————————
    -1.77
     alguns
    -1.72
     durante
    -1.71
     algumas
    -1.69
    🕮
    -1.68
     zwanzig
    -1.66
    POSITIVE LOGITS
    豋
    2.61
    timestamps
    2.33
     hodiny
    2.09
    s
    2.08
     juegos
    2.02
     extracto
    1.92
    ーズン
    1.84
    nagem
    1.80
    🥗
    1.80
     ello
    1.78
    Activations Density 0.002%

    No Known Activations