© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8164
    Prev
    Next
    INDEX
    Explanations

    blogging and following

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

    blogging and website traffic

    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_40_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
    🟡
    0.52
    🟢
    0.51
    🟠
    0.45
    🧬
    0.45
    _${
    0.44
    ₕ
    0.43
    ✅
    0.43
    ⚠️
    0.42
    📥
    0.42
    UNDS
    0.42
    POSITIVE LOGITS
     blog
    2.42
     blogging
    2.31
     Blog
    2.25
     bloggers
    2.20
    Blog
    2.19
     blogger
    2.19
    blog
    2.14
     Blogging
    2.14
    ブログ
    2.13
     Blogger
    2.11
    Activations Density 1.214%

    No Known Activations