© 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. 232655
    Prev
    Next
    INDEX
    Explanations

    account identification

    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
     genocide
    0.52
     apoptosis
    0.52
     defeat
    0.51
     GRA
    0.50
     erasing
    0.50
     discrimination
    0.49
     Z
    0.47
     prevents
    0.46
     [
    0.45
     defeating
    0.45
    POSITIVE LOGITS
    餐厅
    0.55
    гыз
    0.51
    🎤
    0.49
     اکاؤن
    0.48
    账户
    0.48
    的的
    0.48
    Restaurants
    0.47
    账号
    0.47
    ⭐⭐
    0.46
    腾
    0.46
    Activations Density 0.001%

    No Known Activations