© 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. 34-GEMMASCOPE-RES-131K
    7. 59288
    Prev
    Next
    INDEX
    Explanations

    jira ticket tracking

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

    The neuron specifically recognizes Jira REST API endpoint strings (e.g. the “/rest/api/2/permissions” URL).

    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
    unidad
    -0.80
    #![
    -0.76
     pese
    -0.71
    诊
    -0.71
    rater
    -0.71
     unusual
    -0.68
    اني
    -0.67
    𝗮
    -0.67
    штей
    -0.67
    魷
    -0.66
    POSITIVE LOGITS
     ticket
    0.87
     Jira
    0.84
     созда
    0.84
    jira
    0.81
    tempo
    0.80
     jira
    0.79
     ключ
    0.78
     JEN
    0.77
     creado
    0.76
    Tempo
    0.75
    Activations Density 0.024%

    No Known Activations