© 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. 41649
    Prev
    Next
    INDEX
    Explanations

    multilingual contexts

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

    The neuron is tuned to detect numeric tokens, especially decimal numbers.

    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
    m
    -3.53
    </h2>
    -3.38
    t
    -2.94
    獺
    -2.80
    <em>
    -2.77
    </em>
    -2.77
    に
    -2.75
    ט
    -2.72
     )
    -2.64
     Wohnungen
    -2.63
    POSITIVE LOGITS
    達の
    3.13
    苤
    2.95
    
    2.84
    蓠
    2.77
    ほんと
    2.73
    在他的
    2.73
    泣き
    2.72
    くらいの
    2.72
    何回
    2.67
     Découvrez
    2.66
    Activations Density 0.000%

    No Known Activations