© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11168
    Prev
    Next
    INDEX
    Explanations

    area and volume calculation

    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
     राइ
    0.43
    urney
    0.42
    Rotatef
    0.40
    🪜
    0.39
     dirección
    0.39
    路線
    0.38
    uirre
    0.38
    drawLine
    0.38
    ࿔
    0.38
    方向
    0.38
    POSITIVE LOGITS
     area
    1.44
    面积
    1.30
     rectangle
    1.27
     Area
    1.24
     площадь
    1.22
    area
    1.20
    Area
    1.20
    面積
    1.19
     área
    1.18
     areas
    1.17
    Activations Density 0.043%

    No Known Activations