Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8480
    Prev
    Next
    INDEX
    Explanations

    ftp commands and passive mode

    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_34/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
     erkek
    -0.73
    销售
    -0.73
    Ա
    -0.71
     add
    -0.69
     シ
    -0.69
     refunded
    -0.68
     Boring
    -0.68
    METRO
    -0.68
    Eth
    -0.67
    Boring
    -0.66
    POSITIVE LOGITS
     ftp
    1.18
     FTP
    1.13
     TFT
    1.03
    FTP
    1.03
     STOR
    0.99
    ftp
    0.98
    STRU
    0.96
     APPE
    0.95
    haled
    0.94
     SITE
    0.93
    Activations Density 0.035%

    No Known Activations