© 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. 83927
    Prev
    Next
    INDEX
    Explanations

    to remove

    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
    Stuart
    0.43
    荩
    0.42
     proiz
    0.40
    скохозяй
    0.40
    र्मेंद्र
    0.40
     தண்ணீ
    0.39
    ATION
    0.38
    JButton
    0.38
    👏👏
    0.38
     персо
    0.38
    POSITIVE LOGITS
     brother
    0.52
     brotherhood
    0.46
     klasy
    0.46
     fratello
    0.45
    class
    0.45
    1
    0.44
     Brotherhood
    0.43
     bastard
    0.43
     radial
    0.43
     Brother
    0.43
    Activations Density 0.001%

    No Known Activations