© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 104420
    Prev
    Next
    INDEX
    Explanations

    ureters or router.js

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
     was
    0.59
    ῴ
    0.51
     cuatro
    0.51
    1
    0.49
     moléculas
    0.48
     quiser
    0.48
    ä
    0.47
     válv
    0.46
    ¹
    0.46
     encima
    0.46
    POSITIVE LOGITS
    ?!?
    0.52
     ಅಗತ್ಯ
    0.52
     Jorge
    0.51
    觓
    0.51
     పూర్తిగా
    0.50
     POSSIBLE
    0.49
    ?!?!
    0.47
     Jorg
    0.47
    ಿಯೇ
    0.47
     మార
    0.46
    Activations Density 0.001%

    No Known Activations