© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13861
    Prev
    Next
    INDEX
    Explanations

    blogging and publishing

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

    blog posts

    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
     quasi
    0.47
    }=
    0.46
     tacit
    0.43
    DIST
    0.43
     idem
    0.42
     இவரது
    0.42
    neither
    0.42
    }(
    0.41
     imposition
    0.41
     doctrinal
    0.41
    POSITIVE LOGITS
     blog
    0.95
     Blog
    0.92
    blog
    0.87
     blogs
    0.82
     ब्लॉग
    0.82
     blogger
    0.82
     BLOG
    0.80
     blogging
    0.80
    Blog
    0.79
    ブログ
    0.79
    Activations Density 0.585%

    No Known Activations