© 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. 16032
    Prev
    Next
    INDEX
    Explanations

    recommendation

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

    The neuron is looking for expressions of recommendation (e.g. “recommend,” “recommended,” “would recommend”).

    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
     Ammo
    1.00
     যতটুকু
    0.84
    bb
    0.84
    шение
    0.80
     уж
    0.80
    ڃ
    0.80
    建議
    0.79
    妹
    0.77
    чень
    0.77
     reste
    0.76
    POSITIVE LOGITS
    alities
    0.80
     eléctricas
    0.77
    사용
    0.76
    ations
    0.75
     velocidades
    0.74
    这将
    0.74
     habilidades
    0.73
     electricidad
    0.69
     sutures
    0.69
     windings
    0.69
    Activations Density 0.004%

    No Known Activations