© 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. 11157
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on rare or otherwise infrequent tokens – for example uncommon words or proper‐name acronyms.

    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
     Clínica
    0.61
     Gemä
    0.59
     Stimmung
    0.58
    ኰ
    0.54
     Istituto
    0.52
     संयोग
    0.51
     RetValue
    0.51
     mittlerweile
    0.51
     Blüten
    0.51
    Melbourne
    0.49
    POSITIVE LOGITS
    _
    0.59
    1
    0.57
    X
    0.57
    い
    0.57
    ˗
    0.54
    5
    0.52
     X
    0.52
    ─
    0.51
     pointed
    0.51
    <h1>
    0.50
    Activations Density 0.000%

    No Known Activations