© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9836
    Prev
    Next
    INDEX
    Explanations

    around Horseshoe together

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

    The neuron strongly activates on long numeric tokens (e.g. multi-digit page ranges, reference numbers, or PMIDs) in bibliographic citations.

    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
    läge
    0.89
     Simulator
    0.79
    lo
    0.76
     aina
    0.75
     eri
    0.75
    犁
    0.74
    lander
    0.73
    netje
    0.73
    :
    0.72
     Scripps
    0.70
    POSITIVE LOGITS
     しかし
    0.76
    َهُ
    0.75
     refusing
    0.74
     مذہ
    0.72
     costru
    0.72
     उसमे
    0.72
     refusal
    0.71
     rework
    0.71
    しかし
    0.70
    ÈME
    0.70
    Activations Density 0.002%

    No Known Activations