© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 34247
    Prev
    Next
    INDEX
    Explanations

    remove and eliminate

    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_16_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
     morir
    0.62
     pernikahan
    0.60
     responses
    0.59
    +
    0.59
    ش
    0.58
    缡
    0.58
    وا
    0.57
    UMENT
    0.57
     cev
    0.57
    _
    0.55
    POSITIVE LOGITS
    remove
    0.80
     Removing
    0.80
     제거
    0.80
     Eliminate
    0.77
    Elim
    0.75
    eliminate
    0.73
    Removing
    0.72
     removing
    0.71
     eliminate
    0.71
    消除
    0.70
    Activations Density 0.099%

    No Known Activations