© 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. 12380
    Prev
    Next
    INDEX
    Explanations

    job responsibilities and duties

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

    The neuron detects section‐heading language that introduces job duties or responsibilities (e.g. “Job Description,” “Essential Duties and Responsibilities,” “Primary Duties,” etc.).

    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
    のお知らせ
    0.75
     चर्चा
    0.74
    talk
    0.74
     запрос
    0.74
    TOKEN
    0.73
    💌
    0.73
    token
    0.72
    espoir
    0.71
    japan
    0.71
    >>>
    0.70
    POSITIVE LOGITS
     duties
    1.05
     activities
    0.98
     functions
    0.97
     behaviors
    0.92
     performs
    0.90
     routines
    0.90
     overseeing
    0.89
     einschließlich
    0.88
     operations
    0.87
     includes
    0.86
    Activations Density 0.010%

    No Known Activations