© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6879
    Prev
    Next
    INDEX
    Explanations

    food flavors and tastes

    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_16k_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
    ኗ
    0.51
     Canva
    0.49
    大型
    0.48
     层
    0.48
    崞
    0.47
    Insp
    0.46
    镙
    0.46
    เปอร์
    0.45
     прямоуго
    0.44
     Athena
    0.44
    POSITIVE LOGITS
     taste
    1.24
     tasted
    1.05
     flavor
    1.02
     tasting
    1.01
     tastes
    0.97
    taste
    0.97
    味
    0.93
     Taste
    0.93
     smak
    0.92
     goût
    0.91
    Activations Density 0.278%

    No Known Activations