© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 52602
    Prev
    Next
    INDEX
    Explanations

    guard, militia, and emergency services

    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_65k_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
     frameborder
    0.42
    THREADS
    0.40
    GES
    0.39
     উপমহাদেশের
    0.39
     pind
    0.38
     bitches
    0.38
    PE
    0.38
    郑
    0.38
     SOI
    0.38
    Ceylon
    0.37
    POSITIVE LOGITS
     Guard
    0.85
     militia
    0.78
     guard
    0.75
     Guards
    0.71
     militias
    0.71
     Militia
    0.71
     guards
    0.66
     mobilization
    0.66
    weekend
    0.66
     mobilize
    0.66
    Activations Density 0.015%

    No Known Activations