© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42274
    Prev
    Next
    INDEX
    Explanations

    reconcile, referral, Rac, paradigm, venture

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

    bureaucratic jargon

    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
     모든
    0.47
    extré
    0.46
    ᄉ
    0.46
     বছরে
    0.45
    poč
    0.44
     সন্ধ্যা
    0.43
    start
    0.43
    vari
    0.43
    èves
    0.42
    支付
    0.41
    POSITIVE LOGITS
     igualmente
    0.52
     pensato
    0.47
    اہ
    0.47
     bı
    0.46
     stalwart
    0.46
     sıral
    0.46
     ankaŭ
    0.42
    ﻢ
    0.42
     bırak
    0.42
    ڈا
    0.42
    Activations Density 0.000%

    No Known Activations