© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173468
    Prev
    Next
    INDEX
    Explanations

    Mussolini and Italian Fascism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    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
     フェ
    0.39
    ండ్
    0.39
    raper
    0.38
    ষ্কার
    0.37
     mark
    0.37
     slope
    0.37
     dispersion
    0.37
    \%.
    0.37
     diatomic
    0.36
     ausgestattet
    0.35
    POSITIVE LOGITS
     Permission
    0.41
    ărilor
    0.40
    顐
    0.40
     inimes
    0.39
    tracing
    0.39
     Tvam
    0.39
    gms
    0.38
     Agn
    0.38
     realms
    0.38
     Sonia
    0.38
    Activations Density 0.001%

    No Known Activations