© 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. 2819
    Prev
    Next
    INDEX
    Explanations

    language identification and translation

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

    the special conversation token that marks the end of a speaker's turn (e.g., <end_of_turn>).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    Not in Any Lists

    No Comments

    Negative Logits
    勉
    0.38
    HideFlags
    0.36
     morate
    0.36
     autob
    0.34
    bufs
    0.34
    鯵
    0.33
     gars
    0.33
    beginTransaction
    0.33
    スメ
    0.33
     unmet
    0.32
    POSITIVE LOGITS
    וש
    0.43
     ৫
    0.42
    ຜ
    0.40
     п
    0.39
    fut
    0.38
    фу
    0.36
    Dok
    0.36
     ۶
    0.36
     वाक्यांश
    0.36
    app
    0.35
    Activations Density 0.109%

    No Known Activations