© 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. 34-GEMMASCOPE-RES-131K
    7. 23938
    Prev
    Next
    INDEX
    Explanations

    bygone eras and times

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

    The neuron detects references to being stuck in or transported to an earlier time (nostalgic/past‐oriented phrases like “time warp,” “old time,” “past,” “yesterday,” etc.).

    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
     nuevos
    -0.85
     чехол
    -0.82
     meses
    -0.80
    ▂
    -0.80
    ogues
    -0.79
    =@"
    -0.78
    itext
    -0.76
    letto
    -0.76
    Nhap
    -0.75
    Dns
    -0.75
    POSITIVE LOGITS
     simpler
    1.95
     era
    1.81
     yester
    1.59
     past
    1.57
     yesterday
    1.45
     another
    1.41
     vanished
    1.40
     gone
    1.35
    Another
    1.34
     times
    1.34
    Activations Density 0.047%

    No Known Activations