© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61109
    Prev
    Next
    INDEX
    Explanations

    angular components and directives

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

    This neuron fires on Angular framework–specific identifiers (e.g. Component, Directive, module, service, CDK drag-and-drop keywords).

    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
    Жела
    -1.10
     altrett
    -1.08
     juillet
    -1.03
    霑
    -1.03
     créées
    -1.03
     Gigi
    -1.02
    薅
    -1.02
    for
    -1.02
     Bildungs
    -1.01
    Размеры
    -1.00
    POSITIVE LOGITS
     твои
    1.14
    zty
    1.12
    ):
    1.09
    solving
    1.09
    sene
    1.08
    renowned
    1.07
     bescher
    1.06
    junctive
    1.05
     and
    1.05
    shares
    1.05
    Activations Density 0.030%

    No Known Activations