© 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. 4621
    Prev
    Next
    INDEX
    Explanations

    uppercase abbreviation expansions

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

    The neuron detects subword fragments that include a soft‐hyphen marker (i.e. parts of 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
    0.73
    /
    0.71
    ，
    0.70
    ...
    0.70
    .
    0.69
    ("
    0.68
    。
    0.68
    --
    0.67
    :
    0.67
    (
    0.67
    POSITIVE LOGITS
     сайт
    0.68
     enligt
    0.63
     दिलच
    0.63
    து
    0.62
     håller
    0.61
     ساتھ
    0.61
     رکھیں
    0.60
     LPTMR
    0.59
     وجہ
    0.59
     Böyle
    0.59
    Activations Density 0.005%

    No Known Activations