© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 36955
    Prev
    Next
    INDEX
    Explanations

    entering and undoing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    keyword
    0.38
     worsened
    0.38
    nec
    0.36
     링크
    0.35
     hồng
    0.35
    ﻨ
    0.35
    >-</
    0.34
    クラス
    0.34
    otrich
    0.34
    ன்
    0.34
    POSITIVE LOGITS
     Justin
    0.49
     custodians
    0.43
    🍽
    0.42
     rests
    0.40
     ஓய்
    0.39
     বিশ্রাম
    0.39
     Zo
    0.38
     Breeders
    0.38
     condoms
    0.38
     휴
    0.38
    Activations Density 0.000%

    No Known Activations