© 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. 58072
    Prev
    Next
    INDEX
    Explanations

    michael jackson and madonna

    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
    casualties
    0.39
    预算
    0.39
    羡慕
    0.38
    涹
    0.38
    䐍
    0.37
    🔽
    0.36
     учитывать
    0.36
    俢
    0.35
    温暖
    0.35
    露
    0.35
    POSITIVE LOGITS
    Thriller
    0.94
     Thr
    0.91
     Jackson
    0.85
     MJ
    0.83
    Jackson
    0.79
     thriller
    0.78
     michael
    0.70
     JACKSON
    0.70
     Michael
    0.70
    Thr
    0.70
    Activations Density 0.001%

    No Known Activations