© 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. 14405
    Prev
    Next
    INDEX
    Explanations

    entrepreneurship, architecture, shopify, store, dinosaurs

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

    This neuron fires strongly on standalone, often capitalized terms or labels that look like section headings or key topic names.

    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
    Ми
    0.65
    ۃ
    0.62
    rijke
    0.59
    Έ
    0.59
     Ми
    0.57
    dro
    0.56
    YK
    0.56
    ឡិចត្រូ
    0.55
    Με
    0.55
     hr
    0.54
    POSITIVE LOGITS
     rubbers
    0.54
     undermines
    0.53
     errands
    0.52
    פשר
    0.50
    是可以
    0.49
     syndrome
    0.48
    食
    0.47
    ্তে
    0.47
    illers
    0.47
    を防
    0.47
    Activations Density 0.000%

    No Known Activations