© 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. 65926
    Prev
    Next
    INDEX
    Explanations

    programming and technical concepts

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

    The neuron fires on mentions of global or top-level variables (e.g. “global variable,” “#ifdef,” 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_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
     entweder
    -1.09
    Either
    -1.03
    création
    -0.89
    것은
    -0.88
     IANS
    -0.85
    ㌢
    -0.85
     նաև
    -0.85
     содержание
    -0.84
    either
    -0.83
    依照
    -0.83
    POSITIVE LOGITS
     or
    1.39
     type
    0.99
    のような
    0.95
     sorta
    0.91
     like
    0.91
     benzer
    0.90
     camiseta
    0.86
     gibi
    0.86
     but
    0.85
    multicolumn
    0.84
    Activations Density 0.116%

    No Known Activations