© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29004
    Prev
    Next
    INDEX
    Explanations

    universities and research

    np_acts-logits-general · gemini-2.5-flash-lite

    Tylenol synthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Maritime
    0.55
    结果
    0.49
    贯
    0.48
    Zero
    0.48
    ικού
    0.47
    执
    0.47
    定义
    0.47
    Santos
    0.47
    顿
    0.47
    Galaxy
    0.46
    POSITIVE LOGITS
     prevents
    0.57
     puffed
    0.57
     bandages
    0.55
     człowieka
    0.55
     biceps
    0.54
     člov
    0.53
     防止
    0.53
     adipose
    0.52
     d
    0.52
     appreciable
    0.52
    Activations Density 0.023%

    No Known Activations