© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13023
    Prev
    Next
    INDEX
    Explanations

    across and scope

    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
    Negative Logits
     ஒவ்வ
    0.47
     நல்லது
    0.47
     động
    0.42
     وړیا
    0.41
    各有
    0.41
     Each
    0.41
     полную
    0.40
    ('-
    0.40
     каждым
    0.40
    榃
    0.40
    POSITIVE LOGITS
     across
    0.63
     spectrum
    0.56
     different
    0.53
    整个
    0.53
    across
    0.50
    Across
    0.50
    整個
    0.47
     diferentes
    0.47
     всей
    0.46
     geographies
    0.46
    Activations Density 0.010%

    No Known Activations