© 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. 22-GEMMASCOPE-RES-131K
    7. 15445
    Prev
    Next
    INDEX
    Explanations

    webpack plugin

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

    The neuron fires on numeric literals (integers or decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     at
    -2.20
     all
    -1.83
     only
    -1.77
     any
    -1.75
     as
    -1.74
     almost
    -1.69
     may
    -1.66
     ostensibly
    -1.66
     relatively
    -1.63
     just
    -1.62
    POSITIVE LOGITS
     ludicrous
    1.57
     delightfully
    1.56
     AMAZING
    1.53
     lauded
    1.53
     quintessential
    1.52
     masterful
    1.51
     😁
    1.50
     diriger
    1.49
     ayur
    1.49
     Dinas
    1.48
    Activations Density 0.033%

    No Known Activations