© 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. 7180
    Prev
    Next
    INDEX
    Explanations

    repeat or attempt something again

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

    The neuron detects emphatic expressions of intent or recommendation to return or repeat an experience (e.g., “will definitely return,” “can’t wait to go back,” “worth repeat visits”).

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

    expressions of intent to return or repeat a positive experience.

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

    enthusiastic review statements expressing firm intent to return or repeat the experience.

    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
    Joining
    0.88
     ikut
    0.80
     joining
    0.78
     join
    0.77
     bergabung
    0.76
     enrol
    0.74
    JOIN
    0.73
     Joining
    0.73
    Join
    0.72
    加入
    0.70
    POSITIVE LOGITS
     повторя
    0.66
     whenever
    0.62
    何时
    0.60
     repeating
    0.59
     Whenever
    0.59
     многи
    0.56
    ତି
    0.55
     कधी
    0.55
    特定
    0.54
     другими
    0.54
    Activations Density 0.128%

    No Known Activations