© 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. 10-GEMMASCOPE-RES-131K
    4. 1666
    Prev
    Next
    INDEX
    Explanations

    v-for and ng-repeat directives

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

    This neuron detects Vue.js directive attributes (tokens beginning with “v-” such as v-for, v-if, v-bind, v-lazy, etc.).

    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
    鱟
    -1.63
    珦
    -1.61
    piscina
    -1.53
    bahasa
    -1.49
    tedrale
    -1.49
    cfr
    -1.48
    ﮦ
    -1.48
     Для
    -1.48
    gö
    -1.47
    skor
    -1.47
    POSITIVE LOGITS
     of
    1.72
    on
    1.69
    in
    1.65
    8
    1.59
     itinéraire
    1.53
    m
    1.50
    as
    1.50
    at
    1.49
    not
    1.48
    のは
    1.45
    Activations Density 0.010%

    No Known Activations