© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63
    Prev
    Next
    INDEX
    Explanations

    blog posts and content

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

    SEO, content, blogging, dwell time

    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
    ന്ത്രാ
    0.57
    ܩ
    0.54
    lymph
    0.51
     glBindTexture
    0.50
     त्र
    0.49
     kanamycin
    0.49
    reflectionMap
    0.49
     isomorphisms
    0.47
    各位同學
    0.47
     항
    0.46
    POSITIVE LOGITS
     blogger
    0.93
     Blogging
    0.93
     blogging
    0.91
     Blogger
    0.89
     bloggers
    0.85
     Journalism
    0.85
     blog
    0.84
    blogger
    0.84
     Blog
    0.80
     Journalist
    0.80
    Activations Density 0.267%

    No Known Activations