© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94126
    Prev
    Next
    INDEX
    Explanations

    aging demographic

    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/layer_31_width_262k_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
     speł
    0.48
     রুশ
    0.48
     чаще
    0.47
    ewnętr
    0.46
     নির্দিষ্ট
    0.46
     ≠
    0.46
    Throughout
    0.46
    ⁺
    0.45
    matmul
    0.44
     IEquatable
    0.44
    POSITIVE LOGITS
     cheeky
    0.46
     enterprising
    0.46
     comical
    0.46
     emigration
    0.44
     sensibilities
    0.41
     houve
    0.41
     forefathers
    0.41
     adjud
    0.41
     물
    0.40
     inver
    0.40
    Activations Density 0.003%

    No Known Activations