© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6614
    Prev
    Next
    INDEX
    Explanations

    blog posts and announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     Prüfung
    0.61
     helpless
    0.59
     gate
    0.58
     foolproof
    0.58
    ял
    0.58
     needed
    0.57
     قانونی
    0.57
    阀
    0.57
     ücret
    0.57
     scoring
    0.57
    POSITIVE LOGITS
     blog
    2.20
    Blog
    2.15
     Blog
    2.12
    blog
    2.05
     blogs
    2.03
     BLOG
    1.94
     announcements
    1.93
     news
    1.92
    ブログ
    1.88
     newsletter
    1.86
    Activations Density 0.163%

    No Known Activations