© 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. 15749
    Prev
    Next
    INDEX
    Explanations

    gas examples using such/like

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

    The neuron flags references to online platforms and web navigation (e.g., social media sites, search engines, and website navigation).

    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
    REY
    0.63
    ubjects
    0.62
    娅
    0.61
    olese
    0.59
    дий
    0.59
    лив
    0.58
    MOB
    0.57
    Starred
    0.57
     штат
    0.57
    ꯋ
    0.57
    POSITIVE LOGITS
     such
    0.89
     seperti
    0.89
     like
    0.78
     trio
    0.77
     takich
    0.76
     الثلاث
    0.75
    如
    0.75
     takie
    0.74
    เช่น
    0.72
     جیسے
    0.72
    Activations Density 0.228%

    No Known Activations