© 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. 15931
    Prev
    Next
    INDEX
    Explanations

    numbers and code separators

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

    This neuron responds to code‐style tokens—identifiers, numeric literals, and operators—i.e. bits of code rather than ordinary prose.

    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
     after
    -1.17
     zichzelf
    -1.01
     first
    -1.00
     as
    -0.98
    dits
    -0.97
    ǹ
    -0.93
    katapos
    -0.89
    ziu
    -0.89
     comes
    -0.88
     allerede
    -0.88
    POSITIVE LOGITS
    Здравствуйте
    1.05
    íssimo
    0.91
     nour
    0.88
     помещении
    0.88
     thậm
    0.87
    ोल
    0.86
     Statt
    0.85
     disminu
    0.85
    oped
    0.84
     スウェット
    0.82
    Activations Density 0.001%

    No Known Activations