© 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. 53-GEMMASCOPE-2-RES-262K
    7. 33619
    Prev
    Next
    INDEX
    Explanations

    killing squads or firing squads

    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_53_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
     Mert
    0.40
     પ્રાપ્ત
    0.40
    चि
    0.39
    Curly
    0.39
     चेयर
    0.38
    宓
    0.38
    CodeableConcept
    0.38
    metics
    0.38
    Immun
    0.38
    캔
    0.38
    POSITIVE LOGITS
     squad
    1.94
     battalion
    1.82
     squadron
    1.78
     squads
    1.76
     Squad
    1.70
     platoon
    1.70
     Battalion
    1.62
    Squad
    1.59
     detachment
    1.55
     battalions
    1.55
    Activations Density 0.009%

    No Known Activations