© 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. 12896
    Prev
    Next
    INDEX
    Explanations

    here and this time

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

    This neuron isn’t really detecting any particular word or concept but rather how far into a document a token occurs—it fires more strongly on words that appear deeper (in later paragraphs) 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
    Other
    0.62
    وره
    0.59
    OTHER
    0.59
     ერთი
    0.58
    其它
    0.57
     ሌሎች
    0.56
    reste
    0.55
     OTHER
    0.54
    other
    0.54
     কেনো
    0.54
    POSITIVE LOGITS
     ours
    1.31
     今回
    1.24
    今回
    1.20
    今回の
    1.19
    今回は
    1.16
     here
    1.13
     aici
    1.08
     اینجا
    1.02
     здесь
    1.00
     aqui
    0.93
    Activations Density 0.730%

    No Known Activations