© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8642
    Prev
    Next
    INDEX
    Explanations

    instance, institutions

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

    The neuron detects mentions of formal research or educational institutions (especially “Institute of …” names).

    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_31_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
     subsequently
    0.69
     necesitar
    0.65
    엎
    0.62
    asketball
    0.60
    etet
    0.59
    ividade
    0.59
     Sriniv
    0.59
    IEnumerable
    0.58
    сны
    0.58
     auriculares
    0.58
    POSITIVE LOGITS
     Inst
    0.63
    ઉ
    0.63
     dec
    0.58
    mnt
    0.57
    fetchall
    0.56
    ドライ
    0.56
    nofollow
    0.56
    aneously
    0.55
     neurom
    0.54
    ぅ
    0.53
    Activations Density 0.124%

    No Known Activations