© 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. 16-GEMMASCOPE-2-RES-16K
    7. 728
    Prev
    Next
    INDEX
    Explanations

    preventing or avoiding

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

    avoid dictionary words

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    0.82
     imbued
    0.75
    ‌ها
    0.66
     היו
    0.66
    ”،
    0.66
     “,
    0.66
    ᐟ
    0.65
    br
    0.64
    grande
    0.64
     ovation
    0.64
    POSITIVE LOGITS
    防止
    0.79
    .
    0.75
    避免
    0.74
    ו
    0.74
    of
    0.68
    ак
    0.64
    at
    0.63
     voorkomen
    0.63
    வ்வாறு
    0.62
    瞌
    0.62
    Activations Density 0.752%

    No Known Activations