© 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. 22-GEMMASCOPE-RES-131K
    7. 93031
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    This neuron fires on numeric time‐code tokens—i.e. parts of timestamps or log time stamps (digits in hour:minute:second/millisecond formats).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    「
    -1.95
    “
    -1.77
    『
    -1.65
    !（
    -1.63
    💰
    -1.57
     Januari
    -1.55
    Ⅳ
    -1.53
     rodrigo
    -1.52
    $
    -1.52
     januari
    -1.50
    POSITIVE LOGITS
    <bos>
    1.80
     myriad
    1.77
     grotesque
    1.75
    噠
    1.66
     paltry
    1.59
     extremadamente
    1.56
    geführten
    1.55
     geprüft
    1.55
     thorny
    1.53
    嚅
    1.51
    Activations Density 0.007%

    No Known Activations