© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10797
    Prev
    Next
    INDEX
    Explanations

    flat earth conspiracy theories

    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
     আদর
    0.46
    评价
    0.44
     Luxe
    0.43
     মানবিক
    0.42
    Feedback
    0.41
    Recommendation
    0.41
     Bioinformatics
    0.41
    ಔ
    0.40
     Feedback
    0.40
     celebration
    0.39
    POSITIVE LOGITS
     conspiracy
    1.80
     conspiracies
    1.58
     conspir
    1.52
     Conspiracy
    1.46
    spiracy
    1.20
     conspiring
    0.96
     paranoid
    0.93
     consp
    0.89
     paranoia
    0.89
     UFO
    0.88
    Activations Density 0.027%

    No Known Activations