© 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. 40-GEMMASCOPE-2-RES-262K
    7. 195024
    Prev
    Next
    INDEX
    Explanations

    Bosnian War and Sarajevo siege

    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_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
    銚
    0.39
     repro
    0.39
     sureties
    0.38
    ipation
    0.38
     stat
    0.38
     replay
    0.38
    brandt
    0.36
    ព័
    0.36
    ロシア
    0.36
    栦
    0.36
    POSITIVE LOGITS
     Bosnian
    0.77
     Sarajevo
    0.68
     Bosnia
    0.64
    Bos
    0.64
     Muslim
    0.61
    Muslim
    0.61
     Islamic
    0.60
    Islamic
    0.60
    Islam
    0.59
     Islam
    0.57
    Activations Density 0.004%

    No Known Activations