© 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. 34-GEMMASCOPE-RES-131K
    7. 59685
    Prev
    Next
    INDEX
    Explanations

    Angular component lifecycle and scope

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

    The neuron strongly activates on Angular code snippets—particularly the template event-binding syntax (e.g. `(click)=…`) and related HTML/TS tokens.

    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
    Hein
    -0.84
    Imam
    -0.82
    ötä
    -0.81
    țin
    -0.80
     jawab
    -0.80
    ването
    -0.79
     beden
    -0.79
     devouring
    -0.78
     vivió
    -0.78
    licopter
    -0.78
    POSITIVE LOGITS
     on
    1.59
    ngOnInit
    1.46
     ng
    1.38
    ng
    1.16
    On
    1.08
     get
    1.06
    get
    1.05
     receive
    1.04
    偈
    1.02
    on
    0.99
    Activations Density 0.007%

    No Known Activations