© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12889
    Prev
    Next
    INDEX
    Explanations

    researcher's methods and data

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

    The main thing this neuron does is detect references to academic research documents and their sections (e.g. “research,” “study,” “paper,” “questionnaire,” “proposal”).

    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
    临床
    0.69
     pTM
    0.67
     clinically
    0.66
     clínica
    0.64
     cenário
    0.63
     रुग्ण
    0.63
     ጎ
    0.62
    医师
    0.62
     মেডিক্যাল
    0.62
     FullHD
    0.61
    POSITIVE LOGITS
     researcher
    0.88
     sanction
    0.65
    Researcher
    0.63
     Researcher
    0.61
     spad
    0.60
     armature
    0.60
     x
    0.59
     nghiên
    0.58
     descriptive
    0.58
     enlist
    0.58
    Activations Density 0.064%

    No Known Activations