© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21984
    Prev
    Next
    INDEX
    Explanations

    diagonals, segments, opposite edges

    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_all/layer_41_width_262k_l0_big
    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
     হাফ
    0.46
    三角
    0.45
     পাচ
    0.45
     Triangular
    0.42
     fillColor
    0.41
    ilità
    0.40
    рёх
    0.39
    ອ
    0.39
    Height
    0.39
     bericht
    0.39
    POSITIVE LOGITS
     AB
    0.52
     segment
    0.51
     ij
    0.51
     PQ
    0.48
     IJ
    0.47
     XY
    0.46
    IJ
    0.45
    edges
    0.43
     UV
    0.43
     сег
    0.42
    Activations Density 0.003%

    No Known Activations