© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124637
    Prev
    Next
    INDEX
    Explanations

    death penalty executions abolition

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

    capital punishment and prohibitions

    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_31_width_262k_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
     குழ
    0.41
    빕
    0.40
     एक्सेस
    0.39
    цна
    0.39
    秆
    0.39
     BRAD
    0.38
    <^
    0.37
     অতএব
    0.37
    ungsseite
    0.37
    नेस
    0.37
    POSITIVE LOGITS
     teenagers
    0.46
     sobrevivir
    0.45
    <tbody>
    0.42
     hey
    0.42
     survival
    0.42
     Dug
    0.41
     decar
    0.40
     survives
    0.40
     Hey
    0.40
     surviving
    0.40
    Activations Density 0.016%

    No Known Activations