© 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. 8651
    Prev
    Next
    INDEX
    Explanations

    bracketed text

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

    This neuron fires on the uppercase place‐and‐date “dateline” headers that start newswire or newspaper articles.

    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
     cannot
    0.67
     oznacza
    0.64
     श्रद्धांजलि
    0.63
     denom
    0.63
     Faculté
    0.62
     চক্ষু
    0.61
    肨
    0.60
     පිළ
    0.59
     მნიშვნელ
    0.59
     \
    0.59
    POSITIVE LOGITS
    </b>
    0.66
     ранее
    0.64
     sebelumnya
    0.63
     auparavant
    0.63
     afore
    0.59
    embang
    0.59
     tidigare
    0.59
     मुताब
    0.58
     zuvor
    0.58
     mesmos
    0.57
    Activations Density 0.000%

    No Known Activations