© 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. 11804
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by content words appearing at the beginnings of lines or sentences—i.e. words in initial position after a break.

    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
    0.67
     juicy
    0.64
     a
    0.63
     this
    0.63
     any
    0.60
     London
    0.59
     every
    0.59
     November
    0.59
    壩
    0.58
     particular
    0.57
    POSITIVE LOGITS
    の上に
    0.66
     хірур
    0.66
    领域的
    0.64
     Jehová
    0.64
    에게
    0.63
     Chirurgien
    0.63
    หรือ
    0.63
    ління
    0.63
    ,/
    0.63
    ؑ
    0.63
    Activations Density 0.000%

    No Known Activations