© 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. 98889
    Prev
    Next
    INDEX
    Explanations

    penalty area, free kicks, corner, taken

    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
    accuracy
    0.48
    Accuracy
    0.46
     inaccuracy
    0.42
     Accuracy
    0.41
     accuracy
    0.41
    MRC
    0.41
    PUR
    0.40
    糯
    0.39
    ondo
    0.38
    crit
    0.38
    POSITIVE LOGITS
     taker
    0.59
     corner
    0.58
     takers
    0.51
     Corner
    0.50
     awarded
    0.49
     taken
    0.47
     Taken
    0.46
     set
    0.46
     취
    0.46
     Specialist
    0.45
    Activations Density 0.000%

    No Known Activations