© 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. 31-GEMMASCOPE-2-RES-262K
    7. 58346
    Prev
    Next
    INDEX
    Explanations

    code editors and IntelliSense

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

    vscode, vim, nvim, editors

    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_31_width_262k_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
     biomass
    0.46
    鈣
    0.46
     музея
    0.46
     bouillon
    0.46
     heifer
    0.45
     caudal
    0.45
    UMIRE
    0.44
     estrogens
    0.44
     fibrous
    0.44
    鯢
    0.44
    POSITIVE LOGITS
     vscode
    0.88
    vscode
    0.87
    onDidChange
    0.71
    editor
    0.63
    编辑器
    0.61
     Editor
    0.59
    nvim
    0.59
     editor
    0.59
    vim
    0.58
     CMake
    0.56
    Activations Density 0.020%

    No Known Activations