© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102770
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

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

    The neuron selectively fires on standalone punctuation symbols (commas, periods, etc.).

    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
    還沒
    -1.57
    一定要
    -1.55
     secre
    -1.55
    说
    -1.52
    lgari
    -1.52
     tellement
    -1.51
     of
    -1.47
    olybden
    -1.46
     you
    -1.45
    你们
    -1.43
    POSITIVE LOGITS
    er
    1.86
    ’
    1.73
    y
    1.65
    ៚
    1.64
    了她
    1.64
    indest
    1.62
    ÕES
    1.52
     aconte
    1.52
    IDF
    1.51
     convencer
    1.49
    Activations Density 0.003%

    No Known Activations