© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15714
    Prev
    Next
    INDEX
    Explanations

    collections, expansion, brands, AI

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

    The neuron is primarily detecting numeric volume and issue identifiers in scholarly citation entries.

    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
    ب
    0.96
    این
    0.88
     أب
    0.82
     لكن
    0.79
     pekan
    0.79
    væ
    0.77
    ן
    0.77
    vě
    0.74
    oč
    0.74
     şi
    0.73
    POSITIVE LOGITS
     angels
    0.95
     capacitors
    0.87
     cysts
    0.86
     clauses
    0.85
     incarnations
    0.82
     lineages
    0.81
     plasmids
    0.81
     analogues
    0.80
     morphisms
    0.80
     acorns
    0.79
    Activations Density 0.008%

    No Known Activations