© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3080
    Prev
    Next
    INDEX
    Explanations

    This is

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

    finds tokens used for emphasis or section/heading formatting (markdown-style emphasis and similar formatting markers).

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     altres
    0.26
     sommige
    0.22
     aşağıdaki
    0.21
     nedenle
    0.21
     سایر
    0.21
     dalších
    0.21
     whatnot
    0.21
     neler
    0.20
     bestimmte
    0.20
     etcétera
    0.20
    POSITIVE LOGITS
    これは
    0.43
     это
    0.40
     This
    0.39
    这是一个
    0.37
     これは
    0.37
    Это
    0.36
    This
    0.36
    这是
    0.36
     這個
    0.35
     Đây
    0.35
    Activations Density 3.001%

    No Known Activations