© 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. 7596
    Prev
    Next
    INDEX
    Explanations

    audience interaction

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

    The neuron is highly responsive to decimal‐formatted numeric tokens (e.g. floating‐point volume/page numbers) as seen in 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
     zove
    0.77
    ك
    0.75
     encara
    0.68
    ┍
    0.66
    ರ್
    0.65
    Ин
    0.64
     fraîche
    0.64
     potpuno
    0.64
    :
    0.63
     chiama
    0.63
    POSITIVE LOGITS
    ối
    0.87
     móviles
    0.86
    誐
    0.86
    renden
    0.84
    ntity
    0.81
     Planetary
    0.80
    lnk
    0.80
    मिशन
    0.79
     Mysore
    0.79
     Chloride
    0.78
    Activations Density 0.000%

    No Known Activations