© 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. 40-GEMMASCOPE-2-RES-262K
    7. 213894
    Prev
    Next
    INDEX
    Explanations

    event handlers javascript

    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/layer_40_width_262k_l0_medium
    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
    atmos
    0.41
    layout
    0.41
     échanc
    0.40
    titles
    0.40
    بي
    0.39
     স্থাপত্য
    0.39
    祈
    0.38
     Scoop
    0.38
     орби
    0.38
     Sticky
    0.38
    POSITIVE LOGITS
    setSelected
    0.42
     selection
    0.42
     mixed
    0.41
     selected
    0.41
    GFP
    0.40
     []
    0.40
     horses
    0.40
     stores
    0.39
     selector
    0.39
     catast
    0.39
    Activations Density 0.010%

    No Known Activations