© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2844
    Prev
    Next
    INDEX
    Explanations

    bypassing

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

    The neuron identifies the very first substantial content word at the start of each new section or list item, effectively marking segment boundaries.

    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
     ஒருவர்
    0.83
    ქვ
    0.74
    慷
    0.74
    CartVO
    0.73
    稳定的
    0.71
    strnc
    0.71
     старије
    0.70
    人格
    0.70
    priority
    0.70
    मोबाइल
    0.70
    POSITIVE LOGITS
    ong
    0.91
     Gallery
    0.74
    তো
    0.72
     Mg
    0.70
     Heat
    0.70
    nesium
    0.67
    ক্ষন
    0.66
    ι
    0.66
    does
    0.66
     Gulf
    0.66
    Activations Density 0.000%

    No Known Activations