© 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. 6920
    Prev
    Next
    INDEX
    Explanations

    algebraic structures and algebra

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

    This neuron activates on capitalized named-entity tokens, especially athlete and country 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
     dancers
    0.62
     Anglican
    0.58
     Heart
    0.55
    FlatAppearance
    0.55
    FTR
    0.54
    ᐛ
    0.54
     defenseman
    0.54
     Officers
    0.53
     Killing
    0.52
    罣
    0.52
    POSITIVE LOGITS
     anillos
    0.69
     環
    0.68
     anillo
    0.67
     ring
    0.65
     rings
    0.65
    扩
    0.64
     حلقه
    0.60
    环
    0.60
     expansions
    0.59
     RING
    0.59
    Activations Density 0.058%

    No Known Activations