© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 948
    Prev
    Next
    INDEX
    Explanations

    character descriptions or origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     adding
    1.15
     indicating
    1.12
    indicating
    1.02
     highlighting
    1.01
     reinforcing
    1.01
     eventuali
    0.99
    adding
    0.97
    😙
    0.96
     ज्यामुळे
    0.96
     yummy
    0.96
    POSITIVE LOGITS
     पेशे
    1.10
     awalnya
    1.04
    Originally
    1.00
     hails
    0.98
     descended
    0.98
     berusia
    0.98
    Unlike
    0.98
    belong
    0.95
     hailing
    0.95
     Originally
    0.93
    Activations Density 0.497%

    No Known Activations