© 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. 92906
    Prev
    Next
    INDEX
    Explanations

    programming collections

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

    The neuron activates on generic type declarations (e.g. occurrences of collection or parameterized type names).

    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
     moldura
    -1.12
     botella
    -1.11
     Serviço
    -1.08
    舠
    -1.05
     paisagem
    -1.04
     União
    -1.03
    푉
    -1.02
     Conseils
    -1.02
    鼉
    -1.02
    茹で
    -1.01
    POSITIVE LOGITS
     of
    3.17
     or
    1.03
     about
    1.00
    готовка
    0.98
    `${
    0.98
    rachtet
    0.98
     antiguos
    0.94
    いたしました
    0.94
     darunter
    0.93
     فرانسه
    0.93
    Activations Density 0.002%

    No Known Activations