© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1525
    Prev
    Next
    INDEX
    Explanations

    pose estimation

    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
    otroph
    0.48
    married
    0.48
     μαγγ
    0.46
    وث
    0.44
    revista
    0.43
     المقرر
    0.43
    Thy
    0.42
    诫
    0.41
     আর্কাইভ
    0.41
    Married
    0.40
    POSITIVE LOGITS
     facial
    1.09
     detection
    1.01
     detected
    0.98
     detections
    0.95
     Facial
    0.91
     pose
    0.90
     face
    0.89
     landmarks
    0.89
     Detection
    0.83
     Face
    0.82
    Activations Density 0.034%

    No Known Activations