© 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. 40-GEMMASCOPE-2-RES-262K
    7. 21852
    Prev
    Next
    INDEX
    Explanations

    arm circles, juggling

    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_40_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
    咳
    0.39
    炭
    0.39
    有効
    0.39
     civ
    0.38
    退
    0.38
     antibody
    0.38
     बेंच
    0.38
    悚
    0.38
    VALID
    0.37
    烤
    0.37
    POSITIVE LOGITS
     juggling
    0.84
     juggle
    0.70
     balls
    0.63
     tosses
    0.62
     Balls
    0.62
     circles
    0.59
     Circus
    0.59
     Circles
    0.59
     loops
    0.58
     circus
    0.58
    Activations Density 0.015%

    No Known Activations