© 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. 192590
    Prev
    Next
    INDEX
    Explanations

    Passover seder, agreement, meat, ink

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

    risk, licensing, immediately, predictable

    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
    ષ્ઠ
    0.49
    口罩
    0.46
    TabView
    0.46
     Strategy
    0.46
    ຢູ່ໃນ
    0.45
     declining
    0.44
     Sz
    0.44
     Authent
    0.44
     Cooperative
    0.43
    '@
    0.43
    POSITIVE LOGITS
     tentativo
    0.52
    ﻢ
    0.45
     جلو
    0.44
     rett
    0.44
     citt
    0.43
     ristor
    0.43
     sintomi
    0.43
     κι
    0.42
     séqu
    0.41
     però
    0.41
    Activations Density 0.000%

    No Known Activations