© 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. 34-GEMMASCOPE-RES-131K
    4. 60367
    Prev
    Next
    INDEX
    Explanations

    comment markers like #, *, //

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

    The neuron activates on multi‐digit numeric literals (especially four‐digit numbers like years or IDs) in code or comments.

    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
    ****
    -2.11
    ―――
    -2.02
    ***
    -1.98
    スポンサーリンク
    -1.82
     militer
    -1.81
    本日の
    -1.80
    (^_^
    -1.78
    昨日は
    -1.75
     reager
    -1.74
    ♩
    -1.74
    POSITIVE LOGITS
     is
    1.61
    もあります
    1.54
         
    1.53
    ‘
    1.52
     ...
    1.52
     .......
    1.48
     -
    1.47
       
    1.39
    o
    1.39
     &
    1.38
    Activations Density 0.090%

    No Known Activations