© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 57159
    Prev
    Next
    INDEX
    Explanations

    Chinese historical figures, Three Kingdoms

    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_all/layer_41_width_262k_l0_big
    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
     tobacco
    0.44
    Tobacco
    0.42
     ভাষায়
    0.42
     offsetX
    0.40
    ्रे
    0.38
     enlarg
    0.38
    哚
    0.38
     পার্টির
    0.38
    菸
    0.37
    炲
    0.37
    POSITIVE LOGITS
     Cao
    0.57
    三国
    0.54
    Cao
    0.52
     Guan
    0.48
    貂
    0.48
    蹋
    0.46
     Wei
    0.43
    maa
    0.43
     chaos
    0.43
     guan
    0.42
    Activations Density 0.001%

    No Known Activations