© 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. 31-GEMMASCOPE-2-RES-16K
    7. 926
    Prev
    Next
    INDEX
    Explanations

    tutorial, salary information

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

    The neuron is primarily triggered by proper names and titles—tokens that appear as organization, publication, website, or media‐title entities.

    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
    இரு
    0.66
    各
    0.61
     Hadamard
    0.57
    kelig
    0.56
    ciri
    0.56
    ливо
    0.55
    dataframe
    0.55
    虢
    0.55
     各
    0.54
     kaum
    0.53
    POSITIVE LOGITS
     Magazine
    0.67
    ia
    0.66
    ufthansa
    0.64
     Matters
    0.61
    ology
    0.60
     Institute
    0.60
     Alliance
    0.58
    X
    0.58
     Sciences
    0.58
    스타
    0.58
    Activations Density 1.478%

    No Known Activations