© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4572
    Prev
    Next
    INDEX
    Explanations

    garnish, chopped, drizzle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
    ौन
    0.81
     महेंद्र
    0.72
     Determine
    0.72
    үй
    0.71
     हिम्मत
    0.70
    iliki
    0.69
    錳
    0.67
    𝖠
    0.67
     lessen
    0.66
     başlay
    0.66
    POSITIVE LOGITS
     chirality
    0.69
     garnish
    0.69
     strands
    0.64
     shoots
    0.62
     chiral
    0.61
     acabado
    0.60
     spr
    0.60
    র্ষি
    0.60
     Swimming
    0.59
     strand
    0.59
    Activations Density 0.071%

    No Known Activations