© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5946
    Prev
    Next
    INDEX
    Explanations

    Job descriptions and summaries

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

    The neuron strongly activates on section-heading labels in job postings—words like “Job” or “Role” that introduce a job‐description section.

    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_24_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
    s
    0.74
    ham
    0.64
    Article
    0.63
    Solic
    0.63
    或
    0.62
     hoặc
    0.62
     或
    0.62
     or
    0.60
    Forbes
    0.60
    ታዊ
    0.59
    POSITIVE LOGITS
     повністю
    0.74
     بالکل
    0.70
     बिल्कुल
    0.70
     trasm
    0.70
     radially
    0.68
     provenienti
    0.68
    काल
    0.66
     enthält
    0.66
     terminer
    0.66
     खासियत
    0.66
    Activations Density 0.001%

    No Known Activations