© 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. 162160
    Prev
    Next
    INDEX
    Explanations

    financial, economic, and specific terms

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

    focusing on security or defense

    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
    is
    0.53
     swearing
    0.49
     man
    0.48
     ²
    0.47
    ↵
    0.46
    e
    0.45
     .
    0.44
     ,
    0.44
     breather
    0.44
     KGB
    0.43
    POSITIVE LOGITS
     તૈયાર
    0.54
    ন্যার
    0.49
    éci
    0.48
     économiques
    0.48
    ઉન
    0.48
     економі
    0.47
    奖
    0.47
     মিড
    0.47
    醝
    0.47
     экономи
    0.46
    Activations Density 0.000%

    No Known Activations