© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5887
    Prev
    Next
    INDEX
    Explanations

    area of a rectangle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Deps
    0.87
     Reactors
    0.85
     joyería
    0.83
     токси
    0.82
    BlackElo
    0.82
     voce
    0.82
     harboring
    0.81
     Proxy
    0.80
    ≿
    0.80
     Schuld
    0.80
    POSITIVE LOGITS
     rectangle
    1.81
     rectangles
    1.80
    Rectangle
    1.57
    rectangle
    1.54
     rectangular
    1.53
     polygons
    1.42
    rectangular
    1.41
     Rectangle
    1.40
     polygon
    1.36
     quadrilateral
    1.36
    Activations Density 0.422%

    No Known Activations