© 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. 15844
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on long runs of whitespace or indentation characters (e.g. sequences of non-breaking spaces or tabs) used to format or indent code/comments.

    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
     アル
    0.61
     Tabelle
    0.55
    ﻊ
    0.55
    ITICAL
    0.54
     AUDIO
    0.54
     つ
    0.53
    ERVER
    0.53
    Υ
    0.53
     Noticias
    0.53
     Ре
    0.52
    POSITIVE LOGITS
    that
    0.61
    which
    0.54
    there
    0.50
    ўся
    0.49
    makes
    0.47
    так
    0.47
     differentials
    0.46
    닳
    0.46
    make
    0.45
    because
    0.45
    Activations Density 0.028%

    No Known Activations