© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66661
    Prev
    Next
    INDEX
    Explanations

    code mentions and structure

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

    The neuron fires on code‐style identifiers—i.e. API or library names (class, module, or method tokens) such as Cursors, Pods, closest, Colors, models, codes, Windows, Blocks.

    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
    !”
    -1.98
     декабря
    -1.83
    )’
    -1.80
    ariConfig
    -1.77
    phans
    -1.77
    
    -1.77
    .”
    -1.77
     ноября
    -1.73
    Карьера
    -1.72
    一抹
    -1.70
    POSITIVE LOGITS
    2
    2.59
    9
    2.16
    7
    2.09
    3
    2.05
    8
    1.97
    5
    1.88
    1
    1.63
    4
    1.59
    .
    1.56
    since
    1.52
    Activations Density 0.001%

    No Known Activations