© 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. 210127
    Prev
    Next
    INDEX
    Explanations

    admittedly higher-grade option

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

    email server and technical configuration

    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
    ن
    0.50
    泰
    0.47
    胤
    0.44
    鱈
    0.43
    وفر
    0.42
    ‬
    0.42
     equivalents
    0.42
    아
    0.41
     reproducing
    0.41
    פון
    0.41
    POSITIVE LOGITS
    la
    0.58
    ute
    0.49
     ඉතා
    0.49
     MBE
    0.48
    ocycl
    0.47
    kfollowers
    0.47
     także
    0.47
    மைக்
    0.46
    istiwa
    0.46
    ümü
    0.46
    Activations Density 0.000%

    No Known Activations