© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3571
    Prev
    Next
    INDEX
    Explanations

    bulletin boards and forums

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

    The neuron is activated by numeric tokens (sequences of digits, such as numbers in URLs, code, or other numeric identifiers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     requesting
    -0.75
    解釈
    -0.75
    ÓG
    -0.75
    솟
    -0.72
     interpretive
    -0.68
     Charles
    -0.67
     dissect
    -0.67
     UM
    -0.67
     Decken
    -0.66
     DF
    -0.66
    POSITIVE LOGITS
     board
    1.98
    Board
    1.77
     Board
    1.71
    bbs
    1.68
    board
    1.62
     boards
    1.57
     BOARD
    1.54
    BBS
    1.48
     Boards
    1.45
     BBS
    1.45
    Activations Density 0.019%

    No Known Activations