© 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. 34-GEMMASCOPE-RES-131K
    7. 32053
    Prev
    Next
    INDEX
    Explanations

    command arguments and files

    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
    paccio
    -0.81
    Berlin
    -0.80
     femininos
    -0.79
     segü
    -0.77
    libft
    -0.76
    usine
    -0.75
    twig
    -0.74
     utilizan
    -0.73
     Pader
    -0.73
     Suomen
    -0.72
    POSITIVE LOGITS
    CommandLine
    1.10
    argv
    1.10
    命令
    0.87
     argv
    0.83
     commands
    0.82
    gouv
    0.77
     "__
    0.76
    cmdline
    0.75
    zno
    0.75
     underta
    0.73
    Activations Density 0.010%

    No Known Activations