© 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. 103734
    Prev
    Next
    INDEX
    Explanations

    copyright years and identifiers

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

    The neuron is keyed on numeric tokens representing years (often in a hyphenated range), as found in copyright‐date lines.

    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
     happened
    -0.85
     куда
    -0.82
     hó
    -0.76
    ງ
    -0.76
    IGHTS
    -0.76
     HAPPENED
    -0.75
     Nó
    -0.74
    IfExists
    -0.72
    cfa
    -0.72
    igth
    -0.71
    POSITIVE LOGITS
    dellín
    0.81
     fifties
    0.80
    tisserie
    0.78
    čních
    0.77
     Aussage
    0.75
     Haar
    0.75
    ッシュ
    0.75
    ἦ
    0.75
    ウント
    0.73
    esteld
    0.70
    Activations Density 0.095%

    No Known Activations