© 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. 10-GEMMASCOPE-RES-131K
    7. 20949
    Prev
    Next
    INDEX
    Explanations

    software component names

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

    This neuron detects Eclipse/OSGi plugin framework identifiers and related terms (e.g. plugin IDs, activator classes, bundle contexts).

    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
     because
    -1.28
    urés
    -1.27
    iums
    -1.25
     puisque
    -1.24
     carregar
    -1.23
    eneral
    -1.22
    хах
    -1.21
     adicionar
    -1.21
     instruções
    -1.21
    ">
    -1.20
    POSITIVE LOGITS
    tably
    1.43
     their
    1.42
    驛
    1.40
    ࿆
    1.38
    鏊
    1.38
    矢量
    1.34
    鹋
    1.30
    快樂
    1.28
     bombing
    1.23
     brisa
    1.22
    Activations Density 0.034%

    No Known Activations