© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9031
    Prev
    Next
    INDEX
    Explanations

    aria attributes in UI elements

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

    css properties and values

    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_40_width_16k_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
    列
    0.46
    の下
    0.44
    遄
    0.44
    情况下
    0.43
     ቦ
    0.42
    建成
    0.42
    selectable
    0.41
     विभागों
    0.41
    罵
    0.41
    marginBottom
    0.40
    POSITIVE LOGITS
     aria
    0.51
    toggler
    0.49
    aria
    0.47
     caret
    0.47
     toggle
    0.44
     togg
    0.44
     cursor
    0.44
    arier
    0.44
    Toggler
    0.43
     burger
    0.43
    Activations Density 0.005%

    No Known Activations