© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15595
    Prev
    Next
    INDEX
    Explanations

    job loss, financial ruin, crime

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

    The neuron strongly activates on ordinary running English prose (common verbs and flow of narrative) and stays silent on structured product listings, markup, or headings.

    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
    it
    0.84
    hoppers
    0.80
    s
    0.79
    taj
    0.79
    浚
    0.78
    tem
    0.77
    tom
    0.77
    table
    0.76
    h
    0.75
    t
    0.75
    POSITIVE LOGITS
     ίδια
    0.89
    ش
    0.86
     salivary
    0.86
    يا
    0.84
    ΡΙ
    0.84
     ؛
    0.82
     Елена
    0.82
     Рассмотрим
    0.81
     variación
    0.80
     allowNull
    0.79
    Activations Density 0.000%

    No Known Activations