© 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. 75736
    Prev
    Next
    INDEX
    Explanations

    the oldest

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     neuen
    -0.84
    -/**
    -0.80
     νέ
    -0.79
    зывать
    -0.78
    üche
    -0.76
    までの
    -0.75
     reciente
    -0.75
     nuova
    -0.75
    empres
    -0.74
     generó
    -0.74
    POSITIVE LOGITS
     oldest
    5.75
    oldest
    4.41
     Oldest
    3.63
     older
    3.20
     earliest
    3.03
     äl
    2.83
     قدیمی
    2.45
    Older
    2.34
    older
    2.33
     ancient
    2.31
    Activations Density 0.112%

    No Known Activations