© 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. 13385
    Prev
    Next
    INDEX
    Explanations

    profit and risk measures

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

    The neuron is specialized to detect the interrogative “What” at the start of questions.

    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
     écoles
    0.80
     années
    0.77
    oirs
    0.77
    preuves
    0.77
    𝐢
    0.77
     respectivement
    0.77
    estab
    0.76
     espèces
    0.76
    的功能
    0.76
     magnifique
    0.76
    POSITIVE LOGITS
     contrasts
    0.79
    :
    0.74
     complementing
    0.73
    Фи
    0.70
    cknowled
    0.67
     complements
    0.67
     상
    0.67
     >>
    0.66
     speaks
    0.66
     atrophy
    0.65
    Activations Density 0.001%

    No Known Activations