© 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. 361
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on the recurring phrase “in all shapes and sizes,” i.e. text expressing variety with “shapes and sizes.”

    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
     your
    0.50
    /
    0.50
     THEIR
    0.44
     loro
    0.42
     потім
    0.42
     OTHERWISE
    0.42
     YOUR
    0.41
    _
    0.41
     oder
    0.41
     (?)
    0.40
    POSITIVE LOGITS
     számos
    0.58
     Nhiều
    0.57
     tačiau
    0.56
    이지만
    0.53
    诸多
    0.53
    ですが
    0.52
    がありますが
    0.51
     산업
    0.50
    であるが
    0.50
    における
    0.49
    Activations Density 0.000%

    No Known Activations