© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39262
    Prev
    Next
    INDEX
    Explanations

    date and time formats

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

    The neuron fires on standalone numeric tokens that are part of time stamps (i.e. the hour value in date/time entries).

    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
     the
    -3.55
    —
    -2.42
     These
    -2.41
     dört
    -2.33
    -
    -2.23
     '
    -2.23
     With
    -2.20
     Such
    -2.16
     Then
    -2.13
     erste
    -2.13
    POSITIVE LOGITS
    蕺
    2.81
    1
    2.69
     parachoque
    2.55
    ).
    2.53
    鹚
    2.42
     <=",
    2.39
    hanced
    2.39
    玬
    2.38
     vectorstock
    2.36
     dispozici
    2.34
    Activations Density 0.011%

    No Known Activations