© 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. 100150
    Prev
    Next
    INDEX
    Explanations

    aligning and positioning

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

    aligning numbers and text

    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
    Not in Any Lists

    No Comments

    Negative Logits
     YouT
    0.51
    的的
    0.45
    輩
    0.44
    清单
    0.43
    你會
    0.42
     exif
    0.41
     законо
    0.41
    會有
    0.41
    洙
    0.41
     кварта
    0.41
    POSITIVE LOGITS
     uniformly
    0.44
    an
    0.44
    ismus
    0.44
     contrô
    0.43
     et
    0.42
     yüks
    0.42
     based
    0.42
     répart
    0.42
     circumstellar
    0.41
     sourire
    0.41
    Activations Density 0.000%

    No Known Activations