© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110699
    Prev
    Next
    INDEX
    Explanations

    ActiveModel Concern Array Api Engine Test Record Naming Error

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

    the scope resolution operator (::) in Ruby code, particularly when used to access constants, classes, or modules.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on Ruby’s namespace resolution operator (“::”), i.e. on namespaced constant or module references.

    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
     with
    -1.77
    ים
    -1.70
     as
    -1.70
     approche
    -1.41
    畦
    -1.41
     могли
    -1.35
    懺
    -1.34
     one
    -1.34
     apparence
    -1.34
    猡
    -1.33
    POSITIVE LOGITS
     unſ
    1.97
    棡
    1.80
     Perſ
    1.72
    潆
    1.71
     abbildung
    1.70
    问问
    1.69
     juzg
    1.68
     всички
    1.67
    静静
    1.66
     ersche
    1.65
    Activations Density 0.018%

    No Known Activations