© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13630
    Prev
    Next
    INDEX
    Explanations

    last, first, portion, within, date

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

    The neuron activates strongly on content words (longer, non‐function words like nouns, verbs, or proper nouns) and stays off for common function 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
     我们
    0.80
    ennzeichnet
    0.79
    em
    0.78
    ｍ
    0.77
    鈈
    0.77
    たん
    0.77
     மக்களுக்கு
    0.75
    asjon
    0.75
    southeast
    0.75
    ｋ
    0.74
    POSITIVE LOGITS
     envol
    0.83
     lun
    0.82
    <h6>
    0.80
     gráfica
    0.80
     paru
    0.79
     частина
    0.76
     alright
    0.75
     DEVICES
    0.73
    -
    0.73
     inan
    0.72
    Activations Density 0.000%

    No Known Activations