© 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. 207825
    Prev
    Next
    INDEX
    Explanations

    Chrysler Town & Country

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

    searching for 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
    Negative Logits
    pandemic
    0.45
    stest
    0.45
    TEN
    0.44
     situado
    0.43
    OSP
    0.43
    estream
    0.43
    verifica
    0.42
    centrum
    0.42
    ﻀ
    0.41
    裔
    0.41
    POSITIVE LOGITS
     Javed
    0.54
     Iqbal
    0.52
     Piers
    0.52
     trees
    0.51
     minh
    0.51
     myself
    0.50
     Bhar
    0.50
     phrases
    0.50
     arct
    0.49
     Baths
    0.49
    Activations Density 0.000%

    No Known Activations