© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129996
    Prev
    Next
    INDEX
    Explanations

    numerical lists and section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Become
    -1.00
    lerim
    -0.96
    ্ট
    -0.95
    ubahan
    -0.94
    ādā
    -0.93
    کاربرد
    -0.90
     таких
    -0.89
    そんな
    -0.89
    ırlar
    -0.88
    Especially
    -0.88
    POSITIVE LOGITS
     it
    1.18
    民族
    1.02
     their
    1.02
     pamamagitan
    1.00
     ۱۴
    0.99
     we
    0.98
     then
    0.97
     might
    0.94
    😮
    0.92
     by
    0.91
    Activations Density 0.004%

    No Known Activations