© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 196096
    Prev
    Next
    INDEX
    Explanations

    HTTP, HTTPS, SMTP, FTP

    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
    Negative Logits
     conectados
    0.46
     connectedness
    0.45
     conectar
    0.45
     comunicazione
    0.43
    接続
    0.43
    痣
    0.42
     اتصال
    0.42
    繋
    0.41
     connecté
    0.41
    odeal
    0.41
    POSITIVE LOGITS
     HTTP
    1.38
    HTTP
    1.33
     Http
    1.02
    Http
    1.01
    HTTPS
    0.99
     HTTPS
    0.98
    http
    0.95
     http
    0.93
     SMTP
    0.93
     FTP
    0.89
    Activations Density 0.000%

    No Known Activations