© 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. 12099
    Prev
    Next
    INDEX
    Explanations

    numbers, data, or code snippets

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

    The neuron principally detects floating‐point numeric values (decimal numbers) in the text.

    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
     a
    0.89
    ↵
    0.84
     ELLE
    0.83
     of
    0.80
     Mohamed
    0.80
     cf
    0.80
     assolutamente
    0.78
    지의
    0.76
     to
    0.76
    supp
    0.75
    POSITIVE LOGITS
    ла
    0.78
    ﻟ
    0.73
    ்
    0.71
     jScrollPane
    0.70
    Scorch
    0.70
    夕
    0.68
    ות
    0.68
     fussy
    0.68
    Segments
    0.67
    clipse
    0.66
    Activations Density 0.001%

    No Known Activations