© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2780
    Prev
    Next
    INDEX
    Explanations

    radius in geometric formulas

    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_16_width_65k_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
     uncovering
    0.59
    ?
    0.56
    ्य
    0.55
    =\
    0.54
    లు
    0.54
    న
    0.54
     stairway
    0.53
    ัน
    0.52
    यला
    0.52
    atot
    0.52
    POSITIVE LOGITS
    diameter
    0.87
     Radius
    0.79
    半径
    0.77
    li
    0.75
     radius
    0.75
    直径
    0.73
    radius
    0.71
     Diameter
    0.71
    径
    0.70
     Durchmesser
    0.68
    Activations Density 0.012%

    No Known Activations