© 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. 15260
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    The neuron lights up on unusually informative or distinctive content tokens—i.e. rare or domain‐specific keywords—rather than 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
    ה
    0.74
    Су
    0.71
     S
    0.70
    لا
    0.70
    সহ
    0.69
    Comprehensive
    0.67
    ู
    0.66
     ТО
    0.63
    َ
    0.63
    aut
    0.62
    POSITIVE LOGITS
     ਦਵਾਈ
    0.78
     청바
    0.76
     হিন্দ
    0.72
    থা
    0.70
     제품
    0.70
    తారు
    0.70
     gyven
    0.67
     sawdust
    0.67
     settimane
    0.67
    iumi
    0.66
    Activations Density 0.000%

    No Known Activations