© 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. 31-GEMMASCOPE-2-RES-262K
    7. 18814
    Prev
    Next
    INDEX
    Explanations

    larger or targeted changes

    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_31_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
    лды
    0.51
     ១
    0.48
     демокра
    0.44
     आयुष्मान
    0.44
    adap
    0.44
    assumption
    0.43
    androidx
    0.43
     ആൻ
    0.42
    ronique
    0.42
    തിക
    0.42
    POSITIVE LOGITS
     snakes
    0.50
     fox
    0.48
     affix
    0.48
     (
    0.46
     arena
    0.46
     deer
    0.45
     cacti
    0.45
     Fox
    0.45
     con
    0.44
     Product
    0.44
    Activations Density 0.001%

    No Known Activations