© 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. 191099
    Prev
    Next
    INDEX
    Explanations

    fencing, dueling, swords, Dumas

    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
    Berkeley
    0.41
    ijuana
    0.41
     gpd
    0.38
    ʤ
    0.38
    榆
    0.38
     Bernd
    0.37
     makhluk
    0.37
    溽
    0.36
    onedDateTime
    0.35
    rpc
    0.35
    POSITIVE LOGITS
     fencing
    0.86
     duel
    0.77
     swords
    0.70
     sword
    0.67
     musk
    0.66
    🤺
    0.66
     Dumas
    0.65
     Musk
    0.64
     Duel
    0.63
    劍
    0.62
    Activations Density 0.010%

    No Known Activations