© 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. 72846
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron fires on numeric digits—particularly the consecutive numerals used in copyright years.

    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
     aktiviteter
    -1.80
     after
    -1.77
     hjemmeside
    -1.61
     utilización
    -1.60
    懨
    -1.59
     område
    -1.58
    ༛
    -1.56
     detaljer
    -1.55
     different
    -1.55
     specific
    -1.55
    POSITIVE LOGITS
     of
    1.83
    1
    1.82
     
    1.80
    ↵↵
    1.68
    0
    1.50
    но
    1.45
    ğı
    1.38
     grille
    1.36
    .
    1.35
     tabular
    1.34
    Activations Density 0.103%

    No Known Activations