© 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. 34-GEMMASCOPE-RES-131K
    4. 7258
    Prev
    Next
    INDEX
    Explanations

    Ada programming language constructs

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

    This neuron fires on technical programming questions mentioning “Ada” (and related bit-manipulation terminology), i.e. it spots references to the Ada language context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Shit
    -0.68
    Virgo
    -0.68
    ApiClient
    -0.67
    トッピング
    -0.67
    赔
    -0.66
    wati
    -0.65
    parms
    -0.65
     Wat
    -0.65
     Zend
    -0.65
    timme
    -0.65
    POSITIVE LOGITS
    Ada
    1.06
    gnat
    1.04
     Ada
    1.03
     subtype
    0.94
     SPARK
    0.89
    主任
    0.85
    subtype
    0.83
     /=
    0.83
     discriminant
    0.81
     ada
    0.79
    Activations Density 0.032%

    No Known Activations