© 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. 34-GEMMASCOPE-RES-131K
    4. 102971
    Prev
    Next
    INDEX
    Explanations

    verified purchase, standard life, patient guide

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

    The neuron activates on AngularJS directive “definition object” property names (e.g. scope, restrict, template, controller) within directive code.

    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
    الغ
    -0.72
     סל
    -0.71
    Drivers
    -0.70
    Driver
    -0.68
     saudara
    -0.67
    klo
    -0.67
    Assista
    -0.66
     Kluwer
    -0.66
     Browning
    -0.65
    #__
    -0.65
    POSITIVE LOGITS
    促進
    0.69
    Clave
    0.66
     Ader
    0.65
     steve
    0.65
     staying
    0.64
    UserId
    0.63
    衬衫
    0.63
     veniva
    0.63
    在住
    0.62
     scourge
    0.61
    Activations Density 0.052%

    No Known Activations