© 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. 211501
    Prev
    Next
    INDEX
    Explanations

    grants and academic endeavors

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

    foreign language and technical terms

    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
     ಗು
    0.54
    ު
    0.49
    še
    0.48
     Ме
    0.47
    že
    0.47
    ry
    0.45
    íd
    0.45
    QFont
    0.43
    quake
    0.43
     Един
    0.43
    POSITIVE LOGITS
     \
    0.54
     keine
    0.53
     PARA
    0.51
     VERY
    0.51
     SOL
    0.50
     silenz
    0.50
     protezione
    0.49
     URL
    0.49
     prompt
    0.48
    集群
    0.47
    Activations Density 0.001%

    No Known Activations