© 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. 22-GEMMASCOPE-RES-131K
    7. 71357
    Prev
    Next
    INDEX
    Explanations

    module definition or import

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

    The neuron fires on occurrences of the keyword or identifier “default” (e.g. default exports, default properties) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     deslig
    -1.19
    必要がある
    -1.15
     Krzysz
    -1.13
    凄く
    -1.13
     conhecido
    -1.13
    事は
    -1.13
    必要があります
    -1.11
    assembling
    -1.09
     ouvido
    -1.09
    
    -1.09
    POSITIVE LOGITS
     is
    1.21
    However
    1.19
    Something
    1.18
    ～～
    1.16
     as
    1.15
     in
    1.14
     new
    1.14
     خارجی
    1.12
     or
    1.11
    const
    1.08
    Activations Density 0.002%

    No Known Activations