© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4523
    Prev
    Next
    INDEX
    Explanations

    maintained electronically, your chosen

    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_17_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
     nascost
    0.81
    Average
    0.75
    Instant
    0.69
    Toggle
    0.68
     Ά
    0.67
     উইকেট
    0.66
    Already
    0.66
     ጠ
    0.65
    దన
    0.64
    Quality
    0.64
    POSITIVE LOGITS
     dealings
    1.07
     any
    1.06
     cualquier
    1.06
     любых
    1.05
     purporting
    1.00
     undertakings
    0.99
     endeavors
    0.99
     endeavours
    0.98
     ventures
    0.97
     proposed
    0.97
    Activations Density 0.392%

    No Known Activations