© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 535
    Prev
    Next
    INDEX
    Explanations

    Mephisto

    np_acts-logits-general · gemini-2.5-flash-lite

    toxic nerve gas; food cart

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ניים
    0.43
    विभाग
    0.42
     nacimiento
    0.39
     Depart
    0.39
    Snippet
    0.39
     depart
    0.39
    棲
    0.38
    workflow
    0.38
    ვილი
    0.38
    付
    0.38
    POSITIVE LOGITS
     coco
    0.47
    dia
    0.45
     dat
    0.45
    coco
    0.44
    down
    0.43
     dia
    0.42
     somehow
    0.42
     CoA
    0.41
     manners
    0.41
    dat
    0.41
    Activations Density 0.000%

    No Known Activations