© 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. 7296
    Prev
    Next
    INDEX
    Explanations

    The neuron spikes on standalone content words in title‐ or heading‐style text (e.g. capitalized nouns or verbs in headlines and section titles).

    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
    ває
    0.86
    จัดการ
    0.80
     मगर
    0.76
     ಈಗ
    0.76
    However
    0.75
    ແ
    0.73
    箪
    0.73
    хів
    0.73
    Nc
    0.72
    白い
    0.72
    POSITIVE LOGITS
     peroxidation
    0.70
    modulated
    0.65
    eqnarray
    0.64
    র
    0.63
    sulfanyl
    0.63
     revenge
    0.63
     embossed
    0.63
    ு
    0.63
    льки
    0.63
    labelled
    0.62
    Activations Density 0.454%

    No Known Activations