© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12361
    Prev
    Next
    INDEX
    Explanations

    preferred, like, preference

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

    The neuron detects mentions of personal preferences—particularly words expressing likes, dislikes, and related preference terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "like" when it indicates preference or enjoyment.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    statements expressing personal preferences or evaluations, especially liking or disliking something.

    oai_token-act-pair · gpt-5Triggered 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
    犹如
    0.67
     ogni
    0.65
    лез
    0.63
     Wanna
    0.62
     часу
    0.62
    ときは
    0.60
     Badge
    0.60
    なのに
    0.60
    出会
    0.59
     Immer
    0.58
    POSITIVE LOGITS
     meglio
    0.85
     nettement
    0.84
     liking
    0.82
     liked
    0.80
     gosto
    0.79
    不喜欢
    0.79
     preferencia
    0.78
    liked
    0.78
    Preference
    0.77
     preference
    0.76
    Activations Density 0.161%

    No Known Activations