© 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. 10-GEMMASCOPE-RES-131K
    7. 21788
    Prev
    Next
    INDEX
    Explanations

    a/A followed by word

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

    The neuron strongly activates on standalone single-letter “a” (upper- or lower-case) tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Y
    -2.23
    .
    -2.17
     fortfarande
    -2.17
    "
    -2.14
     
    -2.11
    _
    -2.09
    the
    -2.08
    <bos>
    -2.03
    Q
    -1.94
     vermag
    -1.93
    POSITIVE LOGITS
     to
    2.20
    ategorie
    2.09
    猡
    2.02
    ፨
    1.96
    ᠊
    1.89
    鈰
    1.88
    鹚
    1.86
    ydın
    1.86
    剮
    1.85
    轳
    1.84
    Activations Density 0.009%

    No Known Activations