© 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. 7652
    Prev
    Next
    INDEX
    Explanations

    following a consequence

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

    The neuron fires strongly on decimal‐number expressions, i.e. tokens appearing adjacent to or containing a “.” numeral.

    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
    0
    1.09
    5
    1.06
    4
    1.03
    1
    1.02
    2
    0.99
    7
    0.98
    8
    0.97
    9
    0.94
    6
    0.94
    3
    0.86
    POSITIVE LOGITS
    rać
    0.82
     ਉਸ
    0.79
     bekl
    0.78
     Miros
    0.78
    PAAm
    0.78
     barns
    0.78
     Сай
    0.78
    ﺖ
    0.78
     Турции
    0.77
    ﻥ
    0.77
    Activations Density 0.000%

    No Known Activations