© 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. 31-GEMMASCOPE-2-RES-65K
    7. 12178
    Prev
    Next
    INDEX
    Explanations

    food taste aversion and nutrition

    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_31_width_65k_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
    橐
    0.41
    зво
    0.40
    电商
    0.40
     Calle
    0.39
     wreak
    0.39
     আউট
    0.38
     défis
    0.38
     scherm
    0.38
     캐
    0.37
    interrupt
    0.37
    POSITIVE LOGITS
     foods
    0.80
     food
    0.70
     taste
    0.66
     nutritious
    0.66
     picky
    0.66
     disliked
    0.64
     alimentaires
    0.64
     tasteless
    0.63
     nutrition
    0.63
     dislike
    0.63
    Activations Density 0.079%

    No Known Activations