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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73833
    Prev
    Next
    INDEX
    Explanations

    code constructs and text snippets

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

    This neuron fires on code identifiers—names of variables, classes, functions, modules, 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
     voetballer
    -1.02
    ところに
    -0.96
     følge
    -0.95
    場合には
    -0.93
    佝
    -0.91
     biais
    -0.91
     hadden
    -0.91
    sext
    -0.90
    飚
    -0.89
     ligera
    -0.89
    POSITIVE LOGITS
    というわけで
    1.08
    は
    1.08
    2
    0.93
    に対する
    0.91
     コミック
    0.88
    Caracteristici
    0.87
    7
    0.87
     fuo
    0.84
     漫画
    0.84
    ～♪
    0.83
    Activations Density 0.005%

    No Known Activations