© 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. 10-GEMMASCOPE-RES-131K
    7. 59077
    Prev
    Next
    INDEX
    Explanations

    abbreviations ending in s

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

    The neuron fires on tokens that end with the letter “s.”

    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
    旆
    -1.84
    </sup>
    -1.70
    頔
    -1.67
    沺
    -1.64
    苾
    -1.61
    轵
    -1.58
    続きます
    -1.56
    Pgina
    -1.54
     Официальный
    -1.53
     there
    -1.52
    POSITIVE LOGITS
     ‘
    1.88
    ‘
    1.85
    </h3>
    1.84
    {
    1.74
    “
    1.68
     всех
    1.64
     ‘‘
    1.63
     \
    1.56
     входа
    1.55
    *
    1.54
    Activations Density 0.133%

    No Known Activations