© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152804
    Prev
    Next
    INDEX
    Explanations

    canvas over stretcher bars

    np_acts-logits-general · gemini-2.5-flash-lite

    stretching over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    मिताभ
    0.46
    磁盘
    0.45
    兆
    0.45
     Seagate
    0.43
     Westinghouse
    0.42
    光明
    0.42
    亭
    0.42
    apayati
    0.40
    迎
    0.40
    霁
    0.40
    POSITIVE LOGITS
     stretchy
    0.50
     canvases
    0.48
     currentNode
    0.47
     タン
    0.47
    ANO
    0.46
     人気
    0.46
     ストレ
    0.45
     canvas
    0.44
    pped
    0.44
    ouveau
    0.43
    Activations Density 0.002%

    No Known Activations