© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3072
    Prev
    Next
    INDEX
    Explanations

    blog or blogs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    🔃
    0.51
    NOWLED
    0.50
    <unused2175>
    0.47
    <unused2168>
    0.46
    <unused99>
    0.46
     gør
    0.46
    :${
    0.45
     phas
    0.45
    kBtu
    0.44
    <unused338>
    0.44
    POSITIVE LOGITS
     blogs
    0.92
     blog
    0.89
    blog
    0.86
     Blog
    0.86
     Blogger
    0.84
     blogging
    0.81
     Blogs
    0.80
    blogs
    0.80
    Blogs
    0.77
    Blog
    0.75
    Activations Density 0.001%

    No Known Activations