© 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. 22-GEMMASCOPE-RES-131K
    4. 13675
    Prev
    Next
    INDEX
    Explanations

    generic types and collections

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

    The neuron fires on generic type‐parameter declarations and their constraints (e.g. “Monad m => …”, “T : U”, template/class parameter lists).

    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
     there
    -1.20
     cathédrale
    -1.08
     Infe
    -1.04
     secolo
    -0.99
     this
    -0.97
    Inhoud
    -0.97
    علن
    -0.97
     procu
    -0.93
    Комплек
    -0.91
     by
    -0.86
    POSITIVE LOGITS
    %;">
    1.32
    %">
    1.15
    %',
    1.13
     psicológica
    1.08
    ]:
    
    1.06
    )}{
    1.05
    ighed
    1.05
    苷
    1.03
     fakty
    1.03
     vraiment
    1.03
    Activations Density 0.003%

    No Known Activations