© 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. 193069
    Prev
    Next
    INDEX
    Explanations

    ad display URL

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

    public access or domain

    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
    Swing
    0.40
    ﻕ
    0.40
     toàn
    0.40
     (_)
    0.40
     quang
    0.40
    ٓ
    0.39
    toUpperCase
    0.39
    晹
    0.39
     संगम
    0.39
     FileManager
    0.39
    POSITIVE LOGITS
     ordinances
    0.57
    ной
    0.51
     insults
    0.51
    istemas
    0.51
     catheters
    0.51
    rollees
    0.50
    orders
    0.49
    ary
    0.49
     चुनौतियों
    0.48
    რ
    0.48
    Activations Density 0.001%

    No Known Activations