© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4824
    Prev
    Next
    INDEX
    Explanations

    arranges/develops/medical concepts

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

    This neuron spikes strongly on the very beginnings of new text blocks (e.g. forum posts or paragraphs), with its activation level decreasing in later blocks.

    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
    ној
    0.80
    %>%
    0.72
    وش
    0.69
     লোককে
    0.69
     mare
    0.66
    anchez
    0.66
    ENES
    0.66
    رح
    0.65
    Hepin
    0.64
    ALES
    0.64
    POSITIVE LOGITS
    t
    1.14
    ing
    0.95
     Arvind
    0.95
    er
    0.89
     Sergey
    0.88
     Dmitry
    0.86
     shortcomings
    0.85
    																									
    0.85
     Dimitri
    0.84
     Witcher
    0.84
    Activations Density 0.000%

    No Known Activations