© 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. 235489
    Prev
    Next
    INDEX
    Explanations

    exempt income, mobile banking

    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
    氀
    0.52
    al
    0.48
     den
    0.48
    х
    0.47
     toh
    0.45
     implicate
    0.45
    ხ
    0.44
     hiçbir
    0.44
    ﻔ
    0.44
    <unused62>
    0.44
    POSITIVE LOGITS
    ご利用
    0.50
     دوربین
    0.45
     Clk
    0.43
    احمد
    0.42
    တယ်
    0.42
    رمین
    0.41
    য়ো
    0.41
     다음에
    0.41
    steins
    0.40
     रेडियो
    0.40
    Activations Density 0.002%

    No Known Activations