© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9964
    Prev
    Next
    INDEX
    Explanations

    software management commands

    np_acts-logits-general · gemini-2.5-flash-lite

    command line tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NPM
    0.44
     Collabor
    0.42
     GitLab
    0.41
     Comunicación
    0.41
    絢
    0.41
     Git
    0.40
     NodeJS
    0.40
     Dependencies
    0.40
    黃
    0.39
     jQuery
    0.39
    POSITIVE LOGITS
     --
    0.62
    StatusCommand
    0.50
     -
    0.49
     administer
    0.46
    manage
    0.46
    msub
    0.46
    run
    0.45
    --
    0.45
     subcommand
    0.44
    diocese
    0.44
    Activations Density 0.026%

    No Known Activations