© 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. 1715
    Prev
    Next
    INDEX
    Explanations

    The neuron lights up on content‐bearing, semantically important words (rather than on common function words).

    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
     stocked
    0.71
    мони
    0.71
    Ɩ
    0.71
     stocking
    0.70
     жена
    0.69
     ტი
    0.69
     п
    0.68
     ҳо
    0.68
    ారు
    0.67
     해
    0.67
    POSITIVE LOGITS
    un
    0.86
    ied
    0.81
    anches
    0.80
    ทั่วไป
    0.77
    يات
    0.76
    alas
    0.75
    pero
    0.74
    ált
    0.74
    yet
    0.73
    ילה
    0.73
    Activations Density 0.000%

    No Known Activations