© 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. 22-GEMMASCOPE-RES-131K
    7. 129321
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of “_.”, i.e. method calls on the lodash/Underscore object.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    starting tokens of phrases and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    出版年
    -1.00
     kock
    -1.00
    jenkins
    -0.98
     Jenkins
    -0.96
    henden
    -0.95
     its
    -0.93
    Jenkins
    -0.93
     FRANCISCO
    -0.92
     höl
    -0.92
     była
    -0.91
    POSITIVE LOGITS
     fossi
    1.00
    社会的
    0.98
     olden
    0.96
     فقط
    0.94
    禁用
    0.90
    𝓃
    0.90
     osten
    0.89
     numberWith
    0.82
     Aside
    0.81
     condol
    0.81
    Activations Density 0.000%

    No Known Activations