© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 31000
    Prev
    Next
    INDEX
    Explanations

    capsaicin, pain relief, spicy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    an
    0.70
     Política
    0.61
    จะ
    0.59
    et
    0.58
    ある
    0.58
    のは
    0.57
    l
    0.57
    는
    0.57
    ם
    0.57
    ोरी
    0.57
    POSITIVE LOGITS
    ya
    0.60
    ्स
    0.58
    го
    0.55
    ли
    0.55
     thụ
    0.55
    اني
    0.54
    ann
    0.54
    2
    0.53
     koş
    0.53
    یان
    0.52
    Activations Density 0.000%

    No Known Activations