© 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. 75937
    Prev
    Next
    INDEX
    Explanations

    export, smartphone, admitted

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

    follow-up questions

    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
    AC
    0.55
    Sync
    0.54
    Short
    0.52
    Syn
    0.52
    trunk
    0.52
    EC
    0.51
     mecánico
    0.51
    2
    0.51
    8
    0.50
    Number
    0.50
    POSITIVE LOGITS
     각각
    0.54
     hassles
    0.51
     bertemu
    0.48
     mendorong
    0.47
     mengirim
    0.47
    uelva
    0.47
     발
    0.46
    vadipine
    0.46
     сфере
    0.46
     разре
    0.46
    Activations Density 0.001%

    No Known Activations