© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1648
    Prev
    Next
    INDEX
    Explanations

    death and tragedy

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

    The neuron is looking for numeric temporal markers—especially four‐digit years, dates, or ages.

    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
     veya
    0.95
     vagy
    0.92
     oder
    0.87
    /
    0.87
     eller
    0.86
     atau
    0.81
    '
    0.81
     any
    0.79
     or
    0.79
     hoặc
    0.77
    POSITIVE LOGITS
     그는
    0.87
     그의
    0.83
     Ironically
    0.83
     (†
    0.82
     Մ
    0.80
    Ironically
    0.80
    彼は
    0.79
     secretário
    0.78
    iftoire
    0.78
     был
    0.77
    Activations Density 0.028%

    No Known Activations