© 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. 31-GEMMASCOPE-2-RES-65K
    7. 53766
    Prev
    Next
    INDEX
    Explanations

    Russian atrocities and human rights violations

    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_31_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
    ú
    0.54
    in
    0.48
    ką
    0.47
    la
    0.46
    lan
    0.45
    tu
    0.45
     테
    0.45
    ló
    0.44
     바
    0.43
     obten
    0.43
    POSITIVE LOGITS
     degeneration
    0.50
     doctrines
    0.48
     atrocities
    0.47
     decommissioning
    0.47
     negligence
    0.46
    NonNull
    0.46
     promulg
    0.45
     ambulances
    0.45
     perpetuated
    0.45
     annihilation
    0.45
    Activations Density 0.005%

    No Known Activations