© 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-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 9433
    Prev
    Next
    INDEX
    Explanations

    taste, flavor

    np_max-act-logits · gemini-2.5-flash-lite

    taste, flavor

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
     vijj
    0.54
    ชุม
    0.52
    cash
    0.50
     बोझ
    0.49
    $.;
    0.48
    䀼
    0.48
     পারা
    0.47
    អេ
    0.46
     Cash
    0.46
     Moreno
    0.46
    POSITIVE LOGITS
     taste
    4.63
     Taste
    4.00
    Taste
    3.92
     tastes
    3.81
    taste
    3.72
     tasted
    3.52
    味
    3.33
     Geschmack
    3.22
     flavor
    3.09
     вку
    3.09
    Activations Density 0.208%

    No Known Activations