© 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. 3551
    Prev
    Next
    INDEX
    Explanations

    beyond [list of things]

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

    The neuron detects discourse transitions that introduce additional information, such as “apart from” and “in addition to.”

    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
    silver
    0.66
    并未
    0.66
    ../../../
    0.66
     ironically
    0.64
    聂
    0.64
     sheer
    0.63
     चंडीगढ़
    0.61
    的不同
    0.61
     silver
    0.61
    zechos
    0.61
    POSITIVE LOGITS
     være
    0.99
    基本的
    0.81
     Providing
    0.79
    ることが
    0.79
     σημαν
    0.78
     άλλ
    0.77
    のこと
    0.77
     బు
    0.75
    у
    0.75
    ança
    0.74
    Activations Density 0.102%

    No Known Activations