© 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. 67542
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and code snippets

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

    The neuron strongly activates on single-character tokens (i.e. isolated one-letter “words” or identifiers).

    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
     with
    -2.52
     because
    -2.39
     both
    -2.30
     having
    -2.22
    冏
    -2.00
     incorporating
    -1.98
     numerous
    -1.94
    <bos>
    -1.91
     voor
    -1.91
     all
    -1.89
    POSITIVE LOGITS
    "
    2.16
    In
    2.11
    \
    2.03
    0
    2.02
     REALLY
    2.02
    凄く
    1.97
    ごめん
    1.95
    苙
    1.95
    possibly
    1.95
    すみません
    1.91
    Activations Density 0.024%

    No Known Activations