© 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. 243820
    Prev
    Next
    INDEX
    Explanations

    credit and card transactions

    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
    has
    0.50
    i
    0.46
    ↵↵
    0.46
     ​​
    0.45
     除了
    0.45
    is
    0.45
    hs
    0.45
    addListener
    0.45
    pp
    0.44
    </h3>
    0.43
    POSITIVE LOGITS
    сеп
    0.53
     கட்டடக்கலை
    0.53
    τια
    0.52
    ᕋ
    0.50
    忄
    0.50
     আত্মহত্যা
    0.49
    縊
    0.48
    澼
    0.47
    ുകളും
    0.47
    寯
    0.47
    Activations Density 0.000%

    No Known Activations