© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12444
    Prev
    Next
    INDEX
    Explanations

    day 1: followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     baroque
    1.29
     "
    1.24
     অর্থনৈতিক
    1.21
     cái
    1.20
     "..
    1.17
     thóc
    1.17
     "...
    1.10
     Pollution
    1.08
     interesting
    1.08
     mại
    1.08
    POSITIVE LOGITS
     hugs
    1.72
    摯
    1.68
     hugging
    1.59
     hugged
    1.55
     lining
    1.52
     companionship
    1.51
     cuddling
    1.51
     cudd
    1.51
     স্নেহ
    1.50
     mentorship
    1.49
    Activations Density 0.548%

    No Known Activations