© 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. 48325
    Prev
    Next
    INDEX
    Explanations

    dataframes and SQL commands

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

    This neuron fires when the text mentions code‐level object or class names (e.g. “SqlCommand” or “DataFrame”).

    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
    s
    -2.83
    m
    -2.70
    }
    -2.53
    。
    -2.41
     richly
    -2.36
    ]
    -2.36
    ."
    -2.33
    ,''
    -2.31
    <i>
    -2.23
    『
    -2.16
    POSITIVE LOGITS
     Allgemeinen
    2.53
    鹉
    2.38
    itoriale
    2.19
     numerosas
    2.19
    诲
    2.14
    屺
    2.03
    〜。
    2.03
    嬸
    2.02
     și
    1.99
     vorigen
    1.98
    Activations Density 0.003%

    No Known Activations