© 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. 183
    Prev
    Next
    INDEX
    Explanations

    The neuron consistently responds only to the dash (hyphen) character in hyphenated words.

    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
    ς
    0.28
    ../
    0.26
    s
    0.24
    ً
    0.24
    nya
    0.24
    ="">
    0.23
    some
    0.23
    Impl
    0.23
     ৫০
    0.23
    \
    0.23
    POSITIVE LOGITS
    ем
    0.24
    <unused416>
    0.23
    ঈশ্বর
    0.23
    че
    0.23
    пикир
    0.22
    ဆင့်
    0.22
     വിഷയ
    0.21
    ատ
    0.21
    স্বপ
    0.21
    ਤੀ
    0.21
    Activations Density 0.498%

    No Known Activations