© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11550
    Prev
    Next
    INDEX
    Explanations

    romance and relationships

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

    The neuron fires strongly on sentence‐ending punctuation and related boundary markers (periods, closing quotes, paragraph ends).

    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_31_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
     암
    0.66
     esoteric
    0.66
     записы
    0.65
    を用いる
    0.65
    を用いた
    0.63
    Useful
    0.63
    암
    0.63
    構成
    0.61
     instructive
    0.61
     Kodak
    0.61
    POSITIVE LOGITS
     romance
    1.01
     shifter
    0.91
     Romance
    0.88
     romances
    0.88
     Regency
    0.81
    💋
    0.80
     romant
    0.80
     रोमांटिक
    0.80
    👰
    0.79
    💞
    0.77
    Activations Density 0.348%

    No Known Activations