© 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. 221160
    Prev
    Next
    INDEX
    Explanations

    possessives and common prepositions

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

    things that

    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
    То
    0.57
    Table
    0.52
    Q
    0.52
    G
    0.51
    ጥር
    0.50
    X
    0.49
     Pach
    0.48
    cailles
    0.47
    zeichnis
    0.46
    Optical
    0.46
    POSITIVE LOGITS
    hexane
    0.49
     ترین
    0.48
    ستی
    0.46
     ل
    0.46
     یونی
    0.46
     irão
    0.45
     पुस्तिका
    0.44
    ikesh
    0.43
     ہ
    0.43
     جیس
    0.43
    Activations Density 0.000%

    No Known Activations