© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8475
    Prev
    Next
    INDEX
    Explanations

    project management software tools

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

    This neuron detects references to issue‐tracking or task identifiers and related task metadata (e.g. task/subtask names, issue numbers, project tracker terminology).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     합성
    0.62
    ޯ
    0.54
     chemically
    0.52
    阿拉伯
    0.52
    케이
    0.52
    شب
    0.51
     cheveux
    0.50
     洋
    0.50
     জাক
    0.50
    ューズ
    0.49
    POSITIVE LOGITS
     Jira
    1.47
     jira
    1.37
    jira
    1.26
     Bug
    0.97
    Bug
    0.93
     Kanban
    0.93
     tickets
    0.90
     bugs
    0.90
     bug
    0.89
     Tickets
    0.89
    Activations Density 0.149%

    No Known Activations