© 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. 3695
    Prev
    Next
    INDEX
    Explanations

    research topics and development

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

    The neuron is tuned to detect mentions of research or academic institutions, programs, and their related initiatives.

    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
     may
    0.93
     substrings
    0.82
    0
    0.82
     used
    0.81
     x
    0.80
     analyte
    0.78
     suspected
    0.77
     中古
    0.76
    是一位
    0.76
    '
    0.76
    POSITIVE LOGITS
     pembangunan
    1.20
     policym
    0.98
     najważ
    0.97
     izgrad
    0.97
    Governance
    0.96
     همه
    0.96
     важней
    0.96
     penyeleng
    0.95
     tevé
    0.95
     pemerintahan
    0.92
    Activations Density 0.578%

    No Known Activations