© 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. 12211
    Prev
    Next
    INDEX
    Explanations

    function object meaning

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

    This neuron fires on the single most topic-defining content word in each snippet—i.e. the key “headline” token that signals the main subject of the passage.

    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
    at
    0.97
    a
    0.94
    economic
    0.91
    er
    0.90
    al
    0.89
    on
    0.85
    in
    0.84
    ea
    0.84
    of
    0.84
    ol
    0.84
    POSITIVE LOGITS
    肝
    0.82
    栨
    0.82
     右
    0.75
     DISPLAYSURF
    0.75
     उन्‍ह
    0.73
     фор
    0.73
    टरी
    0.72
     बें
    0.72
     `>`,
    0.71
     qīng
    0.70
    Activations Density 0.000%

    No Known Activations